---
title: "Chat-Ghosting: Methods for Auto-Completion in Dialog Systems"
description: "The paper studies \"chat-ghosting\": inline auto-completion that proposes one continuation of the message a user is typing in a… 85 references."
authors: ["Anubhab Mandal", "Sandeep Mishra", "Bishal Santra", "Tushar Abhishek", "Pawan Goyal", "Manish Gupta"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.209/"
doi: "10.18653/v1/2026.eacl-long.209"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/mandal-2026-chat-ghosting-methods-auto-completion/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mandal-2026-chat-ghosting-methods-auto-completion/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/11/) / Chat-Ghosting: Methods for Auto-Completion in Dialog Systems

# Chat-Ghosting: Methods for Auto-Completion in Dialog Systems

**Authors:** [Anubhab Mandal](https://md.research.elamur.ai/free/en/authors/anubhab-mandal/), [Sandeep Mishra](https://md.research.elamur.ai/free/en/authors/sandeep-mishra/), [Bishal Santra](https://md.research.elamur.ai/free/en/authors/bishal-santra/), Tushar Abhishek, [Pawan Goyal](https://md.research.elamur.ai/free/en/authors/pawan-goyal/) and [Manish Gupta](https://md.research.elamur.ai/free/en/authors/manish-gupta/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.209/) · [PDF](https://aclanthology.org/2026.eacl-long.209.pdf) · [DOI 10.18653/v1/2026.eacl-long.209](https://doi.org/10.18653/v1/2026.eacl-long.209) · [OpenAlex](https://openalex.org/W7140080490)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary

The paper studies "chat-ghosting": inline auto-completion that proposes one continuation of the message a user is typing in a chat interface such as ChatGPT or Copilot. Classic query auto-completion usually shows about ten options, so this is a different setting, and it has had little research attention and no standard benchmark. The authors build a benchmark by converting four public dialog corpora into prefix–completion data. Two are human-human (DailyDialog, DSTC7-Ubuntu) and two are human-bot (Open Assistant, ShareGPT), where only the human turns are used.

They compare trie-based completion (MPC, MPC++), the n-gram QueryBlazer, fine-tuned GPT2 and T5, and prompted Phi-2, Mistral-7B and GPT4. Each method is tested with and without earlier dialog turns as context. They also propose an entropy-based early stopping rule that ends a suggestion once model confidence drops.

Tries and n-gram models are both more accurate and faster on prefixes seen during training. T5 and Phi-2 do better on unseen prefixes, and context helps most on the human-bot data. The study gives a baseline for a widely deployed but rarely studied feature and shows a clear trade-off between accuracy and latency.

## Key points

- Datasets and test sizes, in utterances:
  - DD: 7,986
  - DU: 5,588
  - OASST: 981
  - SGPT: 1,088
- SGPT has much longer utterances than the others, about 57 words on average in its test set.
- Evaluation uses prefix-based metrics measured at maximum trigger rate (TR): Match rate (MR), P-Rec and P-Prec. Typing effort saved (TES), METEOR, GPT-4o judgments and latency are also reported. BLEU and ROUGE are considered unsuitable for this task.
- At lower TR the ranking of methods changes. Fine-tuned Phi-2 leads in low-TR regions, and GPT2 gives the best TES for TR\<0.75, although QB is best at maximum TR.
- The entropy-based dynamic early stopping outperforms static truncation of generated suggestions.
- All experiments cover English only. Code and data are released at github.com/blitzprecision/Chat-Ghosting.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Microsoft (India)](https://md.research.elamur.ai/free/en/companies/microsoft-india/) — Company, Hyderabad, India · 10 works · 2,129 citations
- [Indian Institute of Technology Kharagpur](https://md.research.elamur.ai/free/en/universities/indian-institute-of-technology-kharagpur/) — University, Kharagpur, India · 24 works · 714 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works

## Cite

Cite as: Anubhab Mandal, Sandeep Mishra, Bishal Santra, Tushar Abhishek, Pawan Goyal and Manish Gupta. 2026. Chat-Ghosting: Methods for Auto-Completion in Dialog Systems. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{mandal2026chat,
  title = {{Chat-Ghosting: Methods for Auto-Completion in Dialog Systems}},
  author = {Anubhab Mandal, Sandeep Mishra, Bishal Santra, Tushar Abhishek, Pawan Goyal and Manish Gupta},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.209},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.209}
}
```

- [← previous Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards](https://md.research.elamur.ai/free/en/papers/zhang-2026-chart-rl-generalized-chart-comprehension/)
- [next → Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data](https://md.research.elamur.ai/free/en/papers/quinlan-2026-chat-ts-enhancing-multi-modal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/11/)

## References

85 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Daniel Adiwardana, Minh-Thang Luong, David R So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, et al. 2020. [Towards a human-like open-domain chatbot](https://md.research.elamur.ai/free/en/papers/adiwardana-2020-towards-human-like-open-domain/). arXiv preprint arXiv:2001.09977.
3. Lars Backstrom, Jon Kleinberg, Ravi Kumar, and Jasmine Novak. 2008. Spatial variation in search engine queries. In Proceedings of the 17th international conference on World Wide Web, pages 357–366. [find](https://scholar.google.com/scholar?q=Lars+Backstrom%2C+Jon+Kleinberg%2C+Ravi+Kumar%2C+and+Jasmine+Novak%2E+2008%2E+Spatial+variation+in+search+engine+queries%2E+In+Proceedings+of+the+17th+international+conference+on+World+Wide+Web%2C+pages+357%E2%80%93366%2E)
4. Siqi Bao, Huang He, Fan Wang, Hua Wu, and Haifeng Wang. 2019. [Plato: Pre-trained dialogue generation model with discrete latent variable](https://md.research.elamur.ai/free/en/papers/bao-2020-plato-pre-trained-dialogue-generation/). arXiv preprint arXiv:1910.07931.
5. Ziv Bar-Yossef and Naama Kraus. 2011. Context-sensitive query auto-completion. In Proceedings of the 20th international conference on World wide web, pages 107–116. [find](https://scholar.google.com/scholar?q=Ziv+Bar%2DYossef+and+Naama+Kraus%2E+2011%2E+Context%2Dsensitive+query+auto%2Dcompletion%2E+In+Proceedings+of+the+20th+international+conference+on+World+wide+web%2C+pages+107%E2%80%93116%2E)
6. Holger Bast and Ingmar Weber. 2006. Type less, find more: fast autocompletion search with a succinct index. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, pages 364–371. [find](https://scholar.google.com/scholar?q=Holger+Bast+and+Ingmar+Weber%2E+2006%2E+Type+less%2C+find+more%3A+fast+autocompletion+search+with+a+succinct+index%2E+In+Proceedings+of+the+29th+annual+international+ACM+SIGIR+conference+on+Research+and+develop)
7. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
8. Hengyi Cai, Hongshen Chen, Yonghao Song, Xiaofang Zhao, and Dawei Yin. 2021. Exemplar guided neural dialogue generation. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 3601–3607. [find](https://scholar.google.com/scholar?q=Hengyi+Cai%2C+Hongshen+Chen%2C+Yonghao+Song%2C+Xiaofang+Zhao%2C+and+Dawei+Yin%2E+2021%2E+Exemplar+guided+neural+dialogue+generation%2E+In+Proceedings+of+the+Twenty%2DNinth+International+Conference+on+International+Jo)
9. Ciprian Chelba, Mia Chen, Ankur Bapna, and Noam Shazeer. 2020. Faster transformer decoding: N-gram masked self-attention. arXiv preprint arXiv:2001.04589. — [arXiv:2001.04589](https://arxiv.org/abs/2001.04589) [find](https://scholar.google.com/scholar?q=Ciprian+Chelba%2C+Mia+Chen%2C+Ankur+Bapna%2C+and+Noam+Shazeer%2E+2020%2E+Faster+transformer+decoding%3A+N%2Dgram+masked+self%2Dattention%2E+arXiv+preprint+arXiv%3A2001%2E04589%2E+%E2%80%94+%5BarXiv%3A2001%2E04589%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F20)
10. Mia Xu Chen, Benjamin N Lee, Gagan Bansal, Yuan Cao, Shuyuan Zhang, Justin Lu, Jackie Tsay, Yinan Wang, Andrew M Dai, Zhifeng Chen, et al. 2019. Gmail smart compose: Real-time assisted writing. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages… [find](https://scholar.google.com/scholar?q=Mia+Xu+Chen%2C+Benjamin+N+Lee%2C+Gagan+Bansal%2C+Yuan+Cao%2C+Shuyuan+Zhang%2C+Justin+Lu%2C+Jackie+Tsay%2C+Yinan+Wang%2C+Andrew+M+Dai%2C+Zhifeng+Chen%2C+et+al%2E+2019%2E+Gmail+smart+compose%3A+Real%2Dtime+assisted+writing%2E+In+Pro)
11. Qian Chen and Wen Wang. 2019. Sequential attention-based network for noetic end-to-end response selection. ArXiv preprint, abs/1901.02609. — [arXiv:1901.02609](https://arxiv.org/abs/1901.02609) [find](https://scholar.google.com/scholar?q=Qian+Chen+and+Wen+Wang%2E+2019%2E+Sequential+attention%2Dbased+network+for+noetic+end%2Dto%2Dend+response+selection%2E+ArXiv+preprint%2C+abs%2F1901%2E02609%2E+%E2%80%94+%5BarXiv%3A1901%2E02609%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1901%2E02609%29)
12. Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, and Pascal Fleury. 2017. Learning to attend, copy, and generate for session-based query suggestion. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 1747– 1756. [find](https://scholar.google.com/scholar?q=Mostafa+Dehghani%2C+Sascha+Rothe%2C+Enrique+Alfonseca%2C+and+Pascal+Fleury%2E+2017%2E+Learning+to+attend%2C+copy%2C+and+generate+for+session%2Dbased+query+suggestion%2E+In+Proceedings+of+the+2017+ACM+on+Conference+on+I)
13. Giovanni Di Santo, Richard McCreadie, Craig Macdonald, and Iadh Ounis. 2015. Comparing approaches for query autocompletion. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 775–778. [find](https://scholar.google.com/scholar?q=Giovanni+Di+Santo%2C+Richard+McCreadie%2C+Craig+Macdonald%2C+and+Iadh+Ounis%2E+2015%2E+Comparing+approaches+for+query+autocompletion%2E+In+Proceedings+of+the+38th+International+ACM+SIGIR+Conference+on+Research+an)
14. Huizhong Duan and Bo-June Hsu. 2011. Online spelling correction for query completion. In Proceedings of the 20th international conference on World wide web, pages 117–126. [find](https://scholar.google.com/scholar?q=Huizhong+Duan+and+Bo%2DJune+Hsu%2E+2011%2E+Online+spelling+correction+for+query+completion%2E+In+Proceedings+of+the+20th+international+conference+on+World+wide+web%2C+pages+117%E2%80%93126%2E)
15. Luis Fernando D’Haro, Koichiro Yoshino, Chiori Hori, Tim K Marks, Lazaros Polymenakos, Jonathan K Kummerfeld, Michel Galley, and Xiang Gao. 2020. Overview of the seventh dialog system technology challenge: Dstc7. Computer Speech & Language, 62:101068. [find](https://scholar.google.com/scholar?q=Luis+Fernando+D%E2%80%99Haro%2C+Koichiro+Yoshino%2C+Chiori+Hori%2C+Tim+K+Marks%2C+Lazaros+Polymenakos%2C+Jonathan+K+Kummerfeld%2C+Michel+Galley%2C+and+Xiang+Gao%2E+2020%2E+Overview+of+the+seventh+dialog+system+technology+chall)
16. Nicolas Fiorini and Zhiyong Lu. 2018. Personalized neural language models for real-world query auto completion. In Proceedings of NAACL-HLT, pages 208–215. [find](https://scholar.google.com/scholar?q=Nicolas+Fiorini+and+Zhiyong+Lu%2E+2018%2E+Personalized+neural+language+models+for+real%2Dworld+query+auto+completion%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+208%E2%80%93215%2E)
17. Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323. [find](https://scholar.google.com/scholar?q=Elias+Frantar%2C+Saleh+Ashkboos%2C+Torsten+Hoefler%2C+and+Dan+Alistarh%2E+2022%2E+Gptq%3A+Accurate+post%2Dtraining+quantization+for+generative+pre%2Dtrained+transformers%2E+arXiv+preprint+arXiv%3A2210%2E17323%2E)
18. Georgi Gerganov. 2025. llama.cpp: Llm inference in c/c++. [https://github.com/ggerganov/llama](https://github.com/ggerganov/llama). cpp. Accessed: 2025-02-10. [↗](https://github.com/ggerganov/llama)
19. Simon Gog, Giulio Ermanno Pibiri, and Rossano Venturini. 2020. Efficient and effective query auto-completion. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2271–2280. [find](https://scholar.google.com/scholar?q=Simon+Gog%2C+Giulio+Ermanno+Pibiri%2C+and+Rossano+Venturini%2E+2020%2E+Efficient+and+effective+query+auto%2Dcompletion%2E+In+Proceedings+of+the+43rd+International+ACM+SIGIR+Conference+on+Research+and+Development+)
20. Shani Goren, Oren Kalinsky, Tomer Stav, Yuri Rapoport, Yaron Fairstein, Ram Yazdy, Nachshon Cohen, Alexander Libov, and Guy Kushilevitz. 2024. Chai-tea: A benchmark for evaluating autocompletion of interactions with llm-based chatbots. arXiv preprint arXiv:2412.18377. [find](https://scholar.google.com/scholar?q=Shani+Goren%2C+Oren+Kalinsky%2C+Tomer+Stav%2C+Yuri+Rapoport%2C+Yaron+Fairstein%2C+Ram+Yazdy%2C+Nachshon+Cohen%2C+Alexander+Libov%2C+and+Guy+Kushilevitz%2E+2024%2E+Chai%2Dtea%3A+A+benchmark+for+evaluating+autocompletion+of+in)
21. Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio César Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al. 2023. Textbooks are all you need. arXiv preprint arXiv:2306.11644. [find](https://scholar.google.com/scholar?q=Suriya+Gunasekar%2C+Yi+Zhang%2C+Jyoti+Aneja%2C+Caio+C%C3%A9sar+Teodoro+Mendes%2C+Allie+Del+Giorno%2C+Sivakanth+Gopi%2C+Mojan+Javaheripi%2C+Piero+Kauffmann%2C+Gustavo+de+Rosa%2C+Olli+Saarikivi%2C+et+al%2E+2023%2E+Textbooks+are+all)
22. Manish Gupta and Puneet Agrawal. 2022. Compression of deep learning models for text: A survey. ACM Transactions on Knowledge Discovery from Data (TKDD), 16(4):1–55. [find](https://scholar.google.com/scholar?q=Manish+Gupta+and+Puneet+Agrawal%2E+2022%2E+Compression+of+deep+learning+models+for+text%3A+A+survey%2E+ACM+Transactions+on+Knowledge+Discovery+from+Data+%28TKDD%29%2C+16%284%29%3A1%E2%80%9355%2E)
23. Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149. [find](https://scholar.google.com/scholar?q=Song+Han%2C+Huizi+Mao%2C+and+William+J+Dally%2E+2015%2E+Deep+compression%3A+Compressing+deep+neural+networks+with+pruning%2C+trained+quantization+and+huffman+coding%2E+arXiv+preprint+arXiv%3A1510%2E00149%2E)
24. Matthew Henderson, Iñigo Casanueva, Nikola Mrkšić, Pei-Hao Su, Tsung-Hsien Wen, and Ivan Vulić. 2020. [Convert: Efficient and accurate conversational representations from transformers](https://md.research.elamur.ai/free/en/papers/henderson-2020-convert-efficient-accurate-conversational-representations/). In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2161–2174.
25. Connor Holmes, Masahiro Tanaka, Michael Wyatt, Ammar Ahmad Awan, Jeff Rasley, Samyam Rajbhandari, Reza Yazdani Aminabadi, Heyang Qin, Arash Bakhtiari, Lev Kurilenko, et al. 2024. Deepspeed-fastgen: High-throughput text generation for llms via mii and deepspeed-inference. arXiv preprint arXiv:2401.08… [find](https://scholar.google.com/scholar?q=Connor+Holmes%2C+Masahiro+Tanaka%2C+Michael+Wyatt%2C+Ammar+Ahmad+Awan%2C+Jeff+Rasley%2C+Samyam+Rajbhandari%2C+Reza+Yazdani+Aminabadi%2C+Heyang+Qin%2C+Arash+Bakhtiari%2C+Lev+Kurilenko%2C+et+al%2E+2024%2E+Deepspeed%2Dfastgen%3A+Hi)
26. Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2019. Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Samuel+Humeau%2C+Kurt+Shuster%2C+Marie%2DAnne+Lachaux%2C+and+Jason+Weston%2E+2019%2E+Poly%2Dencoders%3A+Architectures+and+pre%2Dtraining+strategies+for+fast+and+accurate+multi%2Dsentence+scoring%2E+In+International+Confere)
27. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. [find](https://scholar.google.com/scholar?q=Albert+Q+Jiang%2C+Alexandre+Sablayrolles%2C+Arthur+Mensch%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Florian+Bressand%2C+Gianna+Lengyel%2C+Guillaume+Lample%2C+Lucile+Saulnier%2C+et+al%2E+2023%2E+Mist)
28. Jyun-Yu Jiang, Yen-Yu Ke, Pao-Yu Chien, and Pu-Jen Cheng. 2014. Learning user reformulation behavior for query auto-completion. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, pages 445–454. [find](https://scholar.google.com/scholar?q=Jyun%2DYu+Jiang%2C+Yen%2DYu+Ke%2C+Pao%2DYu+Chien%2C+and+Pu%2DJen+Cheng%2E+2014%2E+Learning+user+reformulation+behavior+for+query+auto%2Dcompletion%2E+In+Proceedings+of+the+37th+international+ACM+SIGIR+conference+on+Researc)
29. Jyun-Yu Jiang and Wei Wang. 2018. Rin: Reformulation inference network for context-aware query suggestion. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 197–206. [find](https://scholar.google.com/scholar?q=Jyun%2DYu+Jiang+and+Wei+Wang%2E+2018%2E+Rin%3A+Reformulation+inference+network+for+context%2Daware+query+suggestion%2E+In+Proceedings+of+the+27th+ACM+International+Conference+on+Information+and+Knowledge+Manageme)
30. Tian Jin, Gheorghe-Teodor Bercea, Tung D Le, Tong Chen, Gong Su, Haruki Imai, Yasushi Negishi, Anh Leu, Kevin O’Brien, Kiyokuni Kawachiya, et al. 2020. Compiling onnx neural network models using mlir. arXiv preprint arXiv:2008.08272. — [arXiv:2008.08272](https://arxiv.org/abs/2008.08272) [find](https://scholar.google.com/scholar?q=Tian+Jin%2C+Gheorghe%2DTeodor+Bercea%2C+Tung+D+Le%2C+Tong+Chen%2C+Gong+Su%2C+Haruki+Imai%2C+Yasushi+Negishi%2C+Anh+Leu%2C+Kevin+O%E2%80%99Brien%2C+Kiyokuni+Kawachiya%2C+et+al%2E+2020%2E+Compiling+onnx+neural+network+models+using+mlir%2E)
31. Young Mo Kang, Wenhao Liu, and Yingbo Zhou. 2021. Queryblazer: efficient query autocompletion framework. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pages 1020–1028. [find](https://scholar.google.com/scholar?q=Young+Mo+Kang%2C+Wenhao+Liu%2C+and+Yingbo+Zhou%2E+2021%2E+Queryblazer%3A+efficient+query+autocompletion+framework%2E+In+Proceedings+of+the+14th+ACM+International+Conference+on+Web+Search+and+Data+Mining%2C+pages+10)
32. Eugene Kharitonov, Craig Macdonald, Pavel Serdyukov, and Iadh Ounis. 2013. User model-based metrics for offline query suggestion evaluation. In Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval, pages 633–642. [find](https://scholar.google.com/scholar?q=Eugene+Kharitonov%2C+Craig+Macdonald%2C+Pavel+Serdyukov%2C+and+Iadh+Ounis%2E+2013%2E+User+model%2Dbased+metrics+for+offline+query+suggestion+evaluation%2E+In+Proceedings+of+the+36th+international+ACM+SIGIR+conferen)
33. Gyuwan Kim. 2019. Subword language model for query auto-completion. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5022–5032. [find](https://scholar.google.com/scholar?q=Gyuwan+Kim%2E+2019%2E+Subword+language+model+for+query+auto%2Dcompletion%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing+and+the+9th+International+Joint+Conference)
34. Mojtaba Komeili, Kurt Shuster, and Jason Weston. 2021. [Internet-augmented dialogue generation](https://md.research.elamur.ai/free/en/papers/komeili-2022-internet-augmented-dialogue-generation/). ArXiv preprint, abs/2107.07566.
35. Andreas Köpf, Yannic Kilcher, Dimitri von Rütte, Sotiris Anagnostidis, Zhi Rui Tam, Keith Stevens, Abdullah Barhoum, Duc Nguyen, Oliver Stanley, Richárd Nagyfi, et al. 2024. [Openassistant conversations-democratizing large language model alignment](https://md.research.elamur.ai/free/en/papers/kopf-2023-openassistant-conversations-democratizing-large-language/). Advances in Neural Information Processing Systems, 3…
36. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the 29th Symposium on Operating Systems Principles, pages 611–626.
37. Dong-Ho Lee, Zhiqiang Hu, and Roy Ka-Wei Lee. 2021. Improving text auto-completion with next phrase prediction. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4434–4438. [find](https://scholar.google.com/scholar?q=Dong%2DHo+Lee%2C+Zhiqiang+Hu%2C+and+Roy+Ka%2DWei+Lee%2E+2021%2E+Improving+text+auto%2Dcompletion+with+next+phrase+prediction%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2021%2C+pages+4434%E2%80%93443)
38. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. [Dailydialog: A manually labelled multi-turn dialogue dataset](https://md.research.elamur.ai/free/en/papers/li-2017-dailydialog-manually-labelled-multi-turn/). arXiv preprint arXiv:1710.03957.
39. Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of Machine Learning and Systems, 6:87–100. [find](https://scholar.google.com/scholar?q=Ji+Lin%2C+Jiaming+Tang%2C+Haotian+Tang%2C+Shang+Yang%2C+Wei%2DMing+Chen%2C+Wei%2DChen+Wang%2C+Guangxuan+Xiao%2C+Xingyu+Dang%2C+Chuang+Gan%2C+and+Song+Han%2E+2024%2E+Awq%3A+Activation%2Daware+weight+quantization+for+on%2Ddevice+llm+c)
40. Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A Smith, and Yejin Choi. 2021. [Dexperts: Decoding-time controlled text generation with experts and anti-experts](https://md.research.elamur.ai/free/en/papers/liu-2021-dexperts-decoding-time-controlled-text/). arXiv preprint arXiv:2105.03023.
41. Ilya Loshchilov and Frank Hutter. 2022. Sgdr: Stochastic gradient descent with warm restarts. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2022%2E+Sgdr%3A+Stochastic+gradient+descent+with+warm+restarts%2E+In+International+Conference+on+Learning+Representations%2E)
42. Ryan Lowe, Nissan Pow, Iulian Vlad Serban, and Joelle Pineau. 2015. [The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems](https://md.research.elamur.ai/free/en/papers/lowe-2015-ubuntu-dialogue-corpus-large-dataset/). In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 285–294.
43. Ximing Lu, Sean Welleck, Jack Hessel, Liwei Jiang, Lianhui Qin, Peter West, Prithviraj Ammanabrolu, and Yejin Choi. 2022. [Quark: Controllable text generation with reinforced unlearning](https://md.research.elamur.ai/free/en/papers/lu-2022-quark-controllable-text-generation-reinforced/). Advances in neural information processing systems, 35:27591– 27609.
44. Aishwarya Maheswaran, Kaushal Kumar Maurya, Manish Gupta, and Maunendra Sankar Desarkar. 2024a. Dac: Quantized optimal transport reward-based reinforcement learning approach to detoxify query auto-completion. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development i… [find](https://scholar.google.com/scholar?q=Aishwarya+Maheswaran%2C+Kaushal+Kumar+Maurya%2C+Manish+Gupta%2C+and+Maunendra+Sankar+Desarkar%2E+2024a%2E+Dac%3A+Quantized+optimal+transport+reward%2Dbased+reinforcement+learning+approach+to+detoxify+query+auto%2Dcom)
45. Aishwarya Maheswaran, Kaushal Kumar Maurya, Manish Gupta, and Maunendra Sankar Desarkar. 2024b. Dqac: Detoxifying query auto-completion with adapters. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 108–120. Springer. [find](https://scholar.google.com/scholar?q=Aishwarya+Maheswaran%2C+Kaushal+Kumar+Maurya%2C+Manish+Gupta%2C+and+Maunendra+Sankar+Desarkar%2E+2024b%2E+Dqac%3A+Detoxifying+query+auto%2Dcompletion+with+adapters%2E+In+Pacific%2DAsia+Conference+on+Knowledge+Discovery)
46. Kaushal Kumar Maurya, Maunendra Sankar Desarkar, Manish Gupta, and Puneet Agrawal. 2023. Trie-nlg: trie context augmentation to improve personalized query auto-completion for short and unseen prefixes. Data Mining and Knowledge Discovery, 37(6):2306– 2329. [find](https://scholar.google.com/scholar?q=Kaushal+Kumar+Maurya%2C+Maunendra+Sankar+Desarkar%2C+Manish+Gupta%2C+and+Puneet+Agrawal%2E+2023%2E+Trie%2Dnlg%3A+trie+context+augmentation+to+improve+personalized+query+auto%2Dcompletion+for+short+and+unseen+prefixes)
47. Sandeep Mishra, Devichand Budagam, Anubhab Mandal, Bishal Santra, Pawan Goyal, and Manish Gupta. 2026. Router-suggest: A router-based framework for auto-completions in visually-grounded conversations. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational… [find](https://scholar.google.com/scholar?q=Sandeep+Mishra%2C+Devichand+Budagam%2C+Anubhab+Mandal%2C+Bishal+Santra%2C+Pawan+Goyal%2C+and+Manish+Gupta%2E+2026%2E+Router%2Dsuggest%3A+A+router%2Dbased+framework+for+auto%2Dcompletions+in+visually%2Dgrounded+conversations%2E)
48. Bhaskar Mitra and Nick Craswell. 2015. Query auto-completion for rare prefixes. In Proceedings of the 24th ACM international on conference on information and knowledge management, pages 1755–1758. [find](https://scholar.google.com/scholar?q=Bhaskar+Mitra+and+Nick+Craswell%2E+2015%2E+Query+auto%2Dcompletion+for+rare+prefixes%2E+In+Proceedings+of+the+24th+ACM+international+on+conference+on+information+and+knowledge+management%2C+pages+1755%E2%80%931758%2E)
49. Agnès Mustar, Sylvain Lamprier, and Benjamin Piwowarski. 2020. Using bert and bart for query suggestion. In Joint Conference of the Information Retrieval Communities in Europe, volume 2621. CEUR-WS. org. [find](https://scholar.google.com/scholar?q=Agn%C3%A8s+Mustar%2C+Sylvain+Lamprier%2C+and+Benjamin+Piwowarski%2E+2020%2E+Using+bert+and+bart+for+query+suggestion%2E+In+Joint+Conference+of+the+Information+Retrieval+Communities+in+Europe%2C+volume+2621%2E+CEUR%2DWS%2E+o)
50. NVIDIA. 2025. Tensorrt-llm: A tensorrt toolbox for optimized large language model inference. [https://github.com/NVIDIA/TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM). Accessed: 2025-02-10. [↗](https://github.com/NVIDIA/TensorRT-LLM)
51. Alexandra Olteanu, Fernando Diaz, and Gabriella Kazai. 2020. When are search completion suggestions problematic? Proceedings of the ACM on Human-Computer Interaction, 4(CSCW2):1–25. [find](https://scholar.google.com/scholar?q=Alexandra+Olteanu%2C+Fernando+Diaz%2C+and+Gabriella+Kazai%2E+2020%2E+When+are+search+completion+suggestions+problematic%3F+Proceedings+of+the+ACM+on+Human%2DComputer+Interaction%2C+4%28CSCW2%29%3A1%E2%80%9325%2E)
52. Dae Hoon Park and Rikio Chiba. 2017. A neural language model for query auto-completion. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1189–1192. [find](https://scholar.google.com/scholar?q=Dae+Hoon+Park+and+Rikio+Chiba%2E+2017%2E+A+neural+language+model+for+query+auto%2Dcompletion%2E+In+Proceedings+of+the+40th+International+ACM+SIGIR+Conference+on+Research+and+Development+in+Information+Retriev)
53. Lakshmi Ramachandran and Uma Murthy. 2019. Ghosting: contextualized query auto-completion on amazon search. In Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, pages 1377–1378. [find](https://scholar.google.com/scholar?q=Lakshmi+Ramachandran+and+Uma+Murthy%2E+2019%2E+Ghosting%3A+contextualized+query+auto%2Dcompletion+on+amazon+search%2E+In+Proceedings+of+the+42nd+international+ACM+SIGIR+conference+on+research+and+development+in)
54. Alan Ritter, Colin Cherry, and William B. Dolan. 2011. [Data-driven response generation in social media](https://md.research.elamur.ai/free/en/papers/ritter-2011-data-driven-response-generation-social/). In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 583– 593, Edinburgh, Scotland, UK. Association for Computational Linguistics.
55. Adam Roberts, Colin Raffel, Katherine Lee, Michael Matena, Noam Shazeer, Peter J Liu, Sharan Narang, Wei Li, and Yanqi Zhou. 2019. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Google, Tech. Rep.
56. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, and Jason Weston. 2021. [Recipes for building an open-domain chatbot](https://md.research.elamur.ai/free/en/papers/roller-2021-recipes-building-open-domain-chatbot/). In Proceedings of the 16th Conference of the European Chapter of the Association for Computational…
57. Bishal Santra, Potnuru Anusha, and Pawan Goyal. 2021a. Hierarchical transformer for task oriented dialog systems. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5649–5658. [find](https://scholar.google.com/scholar?q=Bishal+Santra%2C+Potnuru+Anusha%2C+and+Pawan+Goyal%2E+2021a%2E+Hierarchical+transformer+for+task+oriented+dialog+systems%2E+In+Proceedings+of+the+2021+Conference+of+the+North+American+Chapter+of+the+Association)
58. Bishal Santra, Sumegh Roychowdhury, Aishik Mandal, Vasu Gurram, Atharva Naik, Manish Gupta, and Pawan Goyal. 2021b. Representation learning for conversational data using discourse mutual information maximization. arXiv preprint arXiv:2112.05787. [find](https://scholar.google.com/scholar?q=Bishal+Santra%2C+Sumegh+Roychowdhury%2C+Aishik+Mandal%2C+Vasu+Gurram%2C+Atharva+Naik%2C+Manish+Gupta%2C+and+Pawan+Goyal%2E+2021b%2E+Representation+learning+for+conversational+data+using+discourse+mutual+information+m)
59. Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C. Courville, and Joelle Pineau. 2016. [Building end-to-end dialogue systems using generative hierarchical neural network models](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/). In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Ari…
60. Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C. Courville, and Yoshua Bengio. 2017. [A hierarchical latent variable encoder-decoder model for generating dialogues](https://md.research.elamur.ai/free/en/papers/serban-2016-hierarchical-latent-variable-encoder-decoder/). In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9,…
61. Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, and Guoping Long. 2017. A conditional variational framework for dialog generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 504–509, Vancou… [find](https://scholar.google.com/scholar?q=Xiaoyu+Shen%2C+Hui+Su%2C+Yanran+Li%2C+Wenjie+Li%2C+Shuzi+Niu%2C+Yang+Zhao%2C+Akiko+Aizawa%2C+and+Guoping+Long%2E+2017%2E+A+conditional+variational+framework+for+dialog+generation%2E+In+Proceedings+of+the+55th+Annual+Meet)
62. Milad Shokouhi. 2013. Learning to personalize query auto-completion. In Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval, pages 103–112. [find](https://scholar.google.com/scholar?q=Milad+Shokouhi%2E+2013%2E+Learning+to+personalize+query+auto%2Dcompletion%2E+In+Proceedings+of+the+36th+international+ACM+SIGIR+conference+on+Research+and+development+in+information+retrieval%2C+pages+103%E2%80%93112%2E)
63. Milad Shokouhi and Kira Radinsky. 2012. Time-sensitive query auto-completion. In Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, pages 601–610. [find](https://scholar.google.com/scholar?q=Milad+Shokouhi+and+Kira+Radinsky%2E+2012%2E+Time%2Dsensitive+query+auto%2Dcompletion%2E+In+Proceedings+of+the+35th+international+ACM+SIGIR+conference+on+Research+and+development+in+information+retrieval%2C+pages+)
64. Jun Song, Jun Xiao, Fei Wu, Haishan Wu, Tong Zhang, Zhongfei Mark Zhang, and Wenwu Zhu. 2017. Hierarchical contextual attention recurrent neural network for map query suggestion. IEEE Transactions on Knowledge and Data Engineering, 29(9):1888– 1901. [find](https://scholar.google.com/scholar?q=Jun+Song%2C+Jun+Xiao%2C+Fei+Wu%2C+Haishan+Wu%2C+Tong+Zhang%2C+Zhongfei+Mark+Zhang%2C+and+Wenwu+Zhu%2E+2017%2E+Hierarchical+contextual+attention+recurrent+neural+network+for+map+query+suggestion%2E+IEEE+Transactions+on+)
65. Alessandro Sordoni, Yoshua Bengio, Hossein Vahabi, Christina Lioma, Jakob Grue Simonsen, and Jian-Yun Nie. 2015. A hierarchical recurrent encoder-decoder for generative context-aware query suggestion. In proceedings of the 24th ACM international on conference on information and knowledge management,… [find](https://scholar.google.com/scholar?q=Alessandro+Sordoni%2C+Yoshua+Bengio%2C+Hossein+Vahabi%2C+Christina+Lioma%2C+Jakob+Grue+Simonsen%2C+and+Jian%2DYun+Nie%2E+2015%2E+A+hierarchical+recurrent+encoder%2Ddecoder+for+generative+context%2Daware+query+suggestion%2E)
66. Stojan Trajanovski, Chad Atalla, Kunho Kim, Vipul Agarwal, Milad Shokouhi, and Chris Quirk. 2021. When does text prediction benefit from additional context? an exploration of contextual signals for chat and email messages. In Proceedings of the 2021 Conference of the North American Chapter of the As… [find](https://scholar.google.com/scholar?q=Stojan+Trajanovski%2C+Chad+Atalla%2C+Kunho+Kim%2C+Vipul+Agarwal%2C+Milad+Shokouhi%2C+and+Chris+Quirk%2E+2021%2E+When+does+text+prediction+benefit+from+additional+context%3F+an+exploration+of+contextual+signals+for+ch)
67. Po-Wei Wang, Huan Zhang, Vijai Mohan, Inderjit S Dhillon, and J Zico Kolter. 2018. Realtime query completion via deep language models. In eCOM@ SIGIR. generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 270–278, Online.… [find](https://scholar.google.com/scholar?q=Po%2DWei+Wang%2C+Huan+Zhang%2C+Vijai+Mohan%2C+Inderjit+S+Dhillon%2C+and+J+Zico+Kolter%2E+2018%2E+Realtime+query+completion+via+deep+language+models%2E+In+eCOM%40+SIGIR%2E+generation%2E+In+Proceedings+of+the+58th+Annual+Mee)
68. Sida Wang, Weiwei Guo, Huiji Gao, and Bo Long. 2020. Efficient neural query auto completion. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 2797– 2804. [find](https://scholar.google.com/scholar?q=Sida+Wang%2C+Weiwei+Guo%2C+Huiji+Gao%2C+and+Bo+Long%2E+2020%2E+Efficient+neural+query+auto+completion%2E+In+Proceedings+of+the+29th+ACM+International+Conference+on+Information+%26+Knowledge+Management%2C+pages+2797%E2%80%93+)
69. Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. [Learning discourse-level diversity for neural dialog models using conditional variational autoencoders](https://md.research.elamur.ai/free/en/papers/zhao-2017-learning-discourse-level-diversity-neural/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–664, Vancouver, C…
70. Yingfei Wang, Hua Ouyang, Hongbo Deng, and Yi Chang. 2017. Learning online trends for interactive query auto-completion. IEEE Transactions on Knowledge and Data Engineering, 29(11):2442– 2454. [find](https://scholar.google.com/scholar?q=Yingfei+Wang%2C+Hua+Ouyang%2C+Hongbo+Deng%2C+and+Yi+Chang%2E+2017%2E+Learning+online+trends+for+interactive+query+auto%2Dcompletion%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+29%2811%29%3A2442%E2%80%93+2454%2E)
71. Overview of Appendix Sections • Section A: Detailed Related Work. [find](https://scholar.google.com/scholar?q=Overview+of+Appendix+Sections+%E2%80%A2+Section+A%3A+Detailed+Related+Work%2E)
72. Michael J Welch and Junghoo Cho. 2008. Automatically identifying localizable queries. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pages 507–514. [find](https://scholar.google.com/scholar?q=Michael+J+Welch+and+Junghoo+Cho%2E+2008%2E+Automatically+identifying+localizable+queries%2E+In+Proceedings+of+the+31st+annual+international+ACM+SIGIR+conference+on+Research+and+development+in+information+re)
73. Section B: Space handling with GPT2 and T5 tokenizers. • Section C: Results for Open Assistant and ShareGPT datasets. [find](https://scholar.google.com/scholar?q=Section+B%3A+Space+handling+with+GPT2+and+T5+tokenizers%2E+%E2%80%A2+Section+C%3A+Results+for+Open+Assistant+and+ShareGPT+datasets%2E)
74. Yuqiao Wen, Guoqing Luo, and Lili Mou. 2022. An empirical study on the overlapping problem of open-domain dialogue datasets. arXiv preprint arXiv:2201.06219. [find](https://scholar.google.com/scholar?q=Yuqiao+Wen%2C+Guoqing+Luo%2C+and+Lili+Mou%2E+2022%2E+An+empirical+study+on+the+overlapping+problem+of+open%2Ddomain+dialogue+datasets%2E+arXiv+preprint+arXiv%3A2201%2E06219%2E)
75. Section D: Prompt for Ghosting Suggestions (without context). • Section E: Contextual Prompt for Ghosting Suggestions. [find](https://scholar.google.com/scholar?q=Section+D%3A+Prompt+for+Ghosting+Suggestions+%28without+context%29%2E+%E2%80%A2+Section+E%3A+Contextual+Prompt+for+Ghosting+Suggestions%2E)
76. Taesun Whang, Dongyub Lee, Dongsuk Oh, Chanhee Lee, Kijong Han, Dong-hun Lee, and Saebyeok Lee. 2021. Do response selection models really know what’s next? utterance manipulation strategies for multi-turn response selection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35… [find](https://scholar.google.com/scholar?q=Taesun+Whang%2C+Dongyub+Lee%2C+Dongsuk+Oh%2C+Chanhee+Lee%2C+Kijong+Han%2C+Dong%2Dhun+Lee%2C+and+Saebyeok+Lee%2E+2021%2E+Do+response+selection+models+really+know+what%E2%80%99s+next%3F+utterance+manipulation+strategies+for+multi%2D)
77. Section F: Hyper-parameter Settings. • Section G: Results for “with context” setting for DD and DU datasets. • Section H: Prefix bucketing results for seen test sets for “without context” setting. [find](https://scholar.google.com/scholar?q=Section+F%3A+Hyper%2Dparameter+Settings%2E+%E2%80%A2+Section+G%3A+Results+for+%E2%80%9Cwith+context%E2%80%9D+setting+for+DD+and+DU+datasets%2E+%E2%80%A2+Section+H%3A+Prefix+bucketing+results+for+seen+test+sets+for+%E2%80%9Cwithout+context%E2%80%9D+setting%2E)
78. Stewart Whiting and Joemon M Jose. 2013. Exploring real-time temporal query auto-completion. In DIR, pages 12–15. Citeseer. [find](https://scholar.google.com/scholar?q=Stewart+Whiting+and+Joemon+M+Jose%2E+2013%2E+Exploring+real%2Dtime+temporal+query+auto%2Dcompletion%2E+In+DIR%2C+pages+12%E2%80%9315%2E+Citeseer%2E)
79. Section I: Prefix bucketing results for “with context” setting. [find](https://scholar.google.com/scholar?q=Section+I%3A+Prefix+bucketing+results+for+%E2%80%9Cwith+context%E2%80%9D+setting%2E)
80. Ruijian Xu, Chongyang Tao, Daxin Jiang, Xueliang Zhao, Dongyan Zhao, and Rui Yan. 2021. Learning an effective context-response matching model with self-supervised tasks for retrieval-based dialogues. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 14158–14166. [find](https://scholar.google.com/scholar?q=Ruijian+Xu%2C+Chongyang+Tao%2C+Daxin+Jiang%2C+Xueliang+Zhao%2C+Dongyan+Zhao%2C+and+Rui+Yan%2E+2021%2E+Learning+an+effective+context%2Dresponse+matching+model+with+self%2Dsupervised+tasks+for+retrieval%2Dbased+dialogues%2E+)
81. Section J: Ghosting accuracy at varying TR thresholds for DU Dataset. • Section K: Truncation-based results for “without context” and “with context” setting. [find](https://scholar.google.com/scholar?q=Section+J%3A+Ghosting+accuracy+at+varying+TR+thresholds+for+DU+Dataset%2E+%E2%80%A2+Section+K%3A+Truncation%2Dbased+results+for+%E2%80%9Cwithout+context%E2%80%9D+and+%E2%80%9Cwith+context%E2%80%9D+setting%2E)
82. Harish Yenala, Manoj Chinnakotla, and Jay Goyal. 2017. Convolutional bi-directional lstm for detecting inappropriate query suggestions in web search. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 3–16. Springer. [find](https://scholar.google.com/scholar?q=Harish+Yenala%2C+Manoj+Chinnakotla%2C+and+Jay+Goyal%2E+2017%2E+Convolutional+bi%2Ddirectional+lstm+for+detecting+inappropriate+query+suggestions+in+web+search%2E+In+Pacific%2DAsia+Conference+on+Knowledge+Discovery+)
83. Di Yin, Jiwei Tan, Zhe Zhang, Hongbo Deng, Shujian Huang, and Jiajun Chen. 2020. Learning to generate personalized query auto-completions via a multi-view multi-task attentive approach. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 2998– 3… [find](https://scholar.google.com/scholar?q=Di+Yin%2C+Jiwei+Tan%2C+Zhe+Zhang%2C+Hongbo+Deng%2C+Shujian+Huang%2C+and+Jiajun+Chen%2E+2020%2E+Learning+to+generate+personalized+query+auto%2Dcompletions+via+a+multi%2Dview+multi%2Dtask+attentive+approach%2E+In+Proceedings)
84. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2020. DIALOGPT : Large-scale generative pre-training for conversational response • Section L: Optimizing Neural Language Models. [find](https://scholar.google.com/scholar?q=Yizhe+Zhang%2C+Siqi+Sun%2C+Michel+Galley%2C+Yen%2DChun+Chen%2C+Chris+Brockett%2C+Xiang+Gao%2C+Jianfeng+Gao%2C+Jingjing+Liu%2C+and+Bill+Dolan%2E+2020%2E+DIALOGPT+%3A+Large%2Dscale+generative+pre%2Dtraining+for+conversational+resp)
85. Section M: Semantic Evaluation. • Section N: Frequently asked questions. [find](https://scholar.google.com/scholar?q=Section+M%3A+Semantic+Evaluation%2E+%E2%80%A2+Section+N%3A+Frequently+asked+questions%2E)

*Updated 1 November 2026*