---
title: "CoDial — paper by Shayanfar et al. (2026) — summary and ideas"
description: "The authors propose CoDial (Code for Dialogue), which treats a TOD system as programmatic LLM guardrailing. 35 references."
authors: ["Radin Shayanfar", "Chu Fei Luo", "Rohan V Bhambhoria", "Samuel Dahan", "Xiaodan Zhu"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1980/"
doi: "10.18653/v1/2026.acl-long.1980"
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/shayanfar-2026-codial-interpretable-task-oriented-dialogue/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shayanfar-2026-codial-interpretable-task-oriented-dialogue/)

[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/25/) / CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment

# CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment

**Authors:** Radin Shayanfar, Chu Fei Luo, Rohan V Bhambhoria, Samuel Dahan and [Xiaodan Zhu](https://md.research.elamur.ai/free/en/authors/xiaodan-zhu/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1980/) · [PDF](https://aclanthology.org/2026.acl-long.1980.pdf) · [DOI 10.18653/v1/2026.acl-long.1980](https://doi.org/10.18653/v1/2026.acl-long.1980) · [OpenAlex](https://openalex.org/W4415131621)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

The paper tackles a long-standing tension in task-oriented dialogue (TOD): systems should handle unseen tasks without retraining, yet schema-based approaches built on neural or generative models make it difficult to see how the schema actually drives behaviour. The authors propose CoDial (Code for Dialogue), which treats a TOD system as programmatic LLM guardrailing. A task schema is first encoded as CHIEF, a heterogeneous directed graph whose node types include request, external action, inform/confirm, and global/fallback actions, with textual conditions on edges. An LLM then translates this JSON-encoded graph into executable NVIDIA Colang code for NeMo-Guardrails, using one of two generation paradigms, CoDial free or CoDial structured. A feedback loop lets humans or LLMs refine the generated program. The system needs neither annotated training data nor hand-written code. It sets a new SOTA on STAR and, with no task-specific training or examples whatsoever, equals the strongest earlier performance on MultiWOZ. Because the dialogue logic is readable code that domain experts can inspect and edit, the approach is well suited to high-stakes fields such as law and medicine.

## Key points

- Three components: the CHIEF dialogue-flow representation, Guardrail-Grounded Code Generation (GCG) producing Colang, and CoDial Human Feedback (CHF) for manual or LLM-aided refinement. GPT-4o was used to convert the original homogeneous schemas into CHIEF.
- Benchmarks: SOTA on STAR and on-par with SOTA on MultiWOZ, zero-shot. Ablations show a large drop when the next-action prediction (NAP) component is replaced by fully generative action prediction, and they suggest NAP and DST reinforce each other.
- Cost on STAR across 24 tasks: about $1.63 per 1,000 dialogues and $0.27 per 1,000 turns, ranging from $0.16 to $0.38 depending on task complexity.
- Human study (3 participants, 50 turns, compared against SAM): CoDial was preferred in about 69–71% of cases versus under 7% for SAM. Ease-of-understanding scores were 4.27 vs 2.46 on a 1–5 Likert scale (p \< 0.001).
- Limitations: all slots are re-queried every turn, which raises latency on large flows, and the system handles only one dialogue flow at a time, so multi-domain dialogue is weak. Code and data are available at github.com/radinshayanfar/CoDial.

*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

- [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/) — University, Ithaca, United States · 120 works · 59,940 citations
- [Queen's University](https://md.research.elamur.ai/free/en/universities/queen-s-university/) — University, Kingston, Canada · 11 works · 1,637 citations
- [Queens University](https://md.research.elamur.ai/free/en/universities/queens-university/) — University, Dhaka, Bangladesh · 4 works · 579 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: Radin Shayanfar, Chu Fei Luo, Rohan V Bhambhoria, Samuel Dahan and Xiaodan Zhu. 2026. CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment. Proceedings of the 64th Annual Meeting 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{shayanfar2026codial,
  title = {{CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment}},
  author = {Radin Shayanfar, Chu Fei Luo, Rohan V Bhambhoria, Samuel Dahan and Xiaodan Zhu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1980},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1980}
}
```

- [← previous Codezone Research Group at AraSentEval Shared Task: Arabic Sentiment Swap beyond Negation Prepending, Benchmarking Multilingual T5 against Large Language Models on the MA'AKS Corpus](https://md.research.elamur.ai/free/en/papers/bichi-2026-codezone-research-group-arasenteval-shared/)
- [next → CogBench: Benchmarking Cognitive Alignment of Large Language Models in Educational Question Answering](https://md.research.elamur.ai/free/en/papers/lu-2026-cogbench-benchmarking-cognitive-alignment-large/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/)

## References

35 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. 2018. [MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling](https://md.research.elamur.ai/free/en/papers/budzianowski-2018-multiwoz-large-scale-multi-domain/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language…
2. Hongshen Chen, Xiaorui Liu, Dawei Yin, and Jiliang Tang. 2017. A survey on dialogue systems: Recent advances and new frontiers. Acm Sigkdd Explorations Newsletter, 19(2):25–35. [find](https://scholar.google.com/scholar?q=Hongshen+Chen%2C+Xiaorui+Liu%2C+Dawei+Yin%2C+and+Jiliang+Tang%2E+2017%2E+A+survey+on+dialogue+systems%3A+Recent+advances+and+new+frontiers%2E+Acm+Sigkdd+Explorations+Newsletter%2C+19%282%29%3A25%E2%80%9335%2E)
3. Samuel Dahan, Rohan Bhambhoria, David Liang, and Xiaodan Zhu. 2023. Lawyers should not trust ai: A call for an open-source legal language model. Available at SSRN 4587092. [find](https://scholar.google.com/scholar?q=Samuel+Dahan%2C+Rohan+Bhambhoria%2C+David+Liang%2C+and+Xiaodan+Zhu%2E+2023%2E+Lawyers+should+not+trust+ai%3A+A+call+for+an+open%2Dsource+legal+language+model%2E+Available+at+SSRN+4587092%2E)
4. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+Preprint%2C+arXiv%3A241)
5. Y Dong, R Mu, Y Zhang, S Sun, T Zhang, C Wu, G Jin, Y Qi, J Hu, and J Meng. 2024a. Safeguarding [large language models: a survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). arxiv. Preprint posted online June, 3.
6. Yi Dong, Ronghui Mu, Gaojie Jin, Yi Qi, Jinwei Hu, Xingyu Zhao, Jie Meng, Wenjie Ruan, and Xiaowei Huang. 2024b. Building guardrails for large language models. Preprint, arXiv:2402.01822. — [arXiv:2402.01822](https://arxiv.org/abs/2402.01822) [find](https://scholar.google.com/scholar?q=Yi+Dong%2C+Ronghui+Mu%2C+Gaojie+Jin%2C+Yi+Qi%2C+Jinwei+Hu%2C+Xingyu+Zhao%2C+Jie+Meng%2C+Wenjie+Ruan%2C+and+Xiaowei+Huang%2E+2024b%2E+Building+guardrails+for+large+language+models%2E+Preprint%2C+arXiv%3A2402%2E01822%2E+%E2%80%94+%5BarXiv%3A240)
7. Yujie Feng, Zexin Lu, Bo Liu, Liming Zhan, and Xiao-Ming Wu. 2023. Towards LLM-driven dialogue state tracking. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 739–755, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yujie+Feng%2C+Zexin+Lu%2C+Bo+Liu%2C+Liming+Zhan%2C+and+Xiao%2DMing+Wu%2E+2023%2E+Towards+LLM%2Ddriven+dialogue+state+tracking%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Language+Processing)
8. Guardrails AI. Guardrails: Adding guardrails to large language models. [https://github.com/](https://github.com/) guardrails-ai/guardrails. Accessed: 2025-05-16. [↗](https://github.com/)
9. Aman Gupta, Anirudh Ravichandran, Narayanan Sadagopan, and Anurag Beniwal. 2024. DARD: A multi-agent approach for task-oriented dialog systems. In NeurIPS 2024 Workshop on Open-World Agents. [find](https://scholar.google.com/scholar?q=Aman+Gupta%2C+Anirudh+Ravichandran%2C+Narayanan+Sadagopan%2C+and+Anurag+Beniwal%2E+2024%2E+DARD%3A+A+multi%2Dagent+approach+for+task%2Doriented+dialog+systems%2E+In+NeurIPS+2024+Workshop+on+Open%2DWorld+Agents%2E)
10. Amine El Hattami, Issam H. Laradji, Stefania Rai-mondo, David Vazquez, Pau Rodriguez, and Christopher Pal. 2023. Workflow discovery from dialogues in the low data regime. Transactions on Machine Learning Research. Featured Certification. [find](https://scholar.google.com/scholar?q=Amine+El+Hattami%2C+Issam+H%2E+Laradji%2C+Stefania+Rai%2Dmondo%2C+David+Vazquez%2C+Pau+Rodriguez%2C+and+Christopher+Pal%2E+2023%2E+Workflow+discovery+from+dialogues+in+the+low+data+regime%2E+Transactions+on+Machine+Learn)
11. Vojtěch Hudeček and Ondrej Dusek. 2023. Are large language models all you need for task-oriented dialogue? In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 216–228, Prague, Czechia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Vojte%CC%8Cch+Hudec%CC%8Cek+and+Ondrej+Dusek%2E+2023%2E+Are+large+language+models+all+you+need+for+task%2Doriented+dialogue%3F+In+Proceedings+of+the+24th+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+and+Di)
12. Léo Jacqmin, Lina M. Rojas Barahona, and Benoit Favre. 2022. “do you follow me?”: A survey of recent approaches in dialogue state tracking. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 336–350, Edinburgh, UK. Association for Computational L… [find](https://scholar.google.com/scholar?q=L%C3%A9o+Jacqmin%2C+Lina+M%2E+Rojas+Barahona%2C+and+Benoit+Favre%2E+2022%2E+%E2%80%9Cdo+you+follow+me%3F%E2%80%9D%3A+A+survey+of+recent+approaches+in+dialogue+state+tracking%2E+In+Proceedings+of+the+23rd+Annual+Meeting+of+the+Special+Int)
13. Ziwei Ji, Tiezheng Yu, Yan Xu, Nayeon Lee, Etsuko Ishii, and Pascale Fung. 2023. [Towards mitigating llm hallucination via self reflection](https://md.research.elamur.ai/free/en/papers/ji-2023-mitigating-llm-hallucination-self-reflection/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1827–1843.
14. Xue Jiang, Yihong Dong, Lecheng Wang, Zheng Fang, Qiwei Shang, Ge Li, Zhi Jin, and Wenpin Jiao. 2024. Self-planning code generation with large language models. ACM Transactions on Software Engineering and Methodology, 33(7):1–30. [find](https://scholar.google.com/scholar?q=Xue+Jiang%2C+Yihong+Dong%2C+Lecheng+Wang%2C+Zheng+Fang%2C+Qiwei+Shang%2C+Ge+Li%2C+Zhi+Jin%2C+and+Wenpin+Jiao%2E+2024%2E+Self%2Dplanning+code+generation+with+large+language+models%2E+ACM+Transactions+on+Software+Engineering)
15. Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and Steven Chu Hong Hoi. 2022. [Coderl: Mastering code generation through pretrained models and deep reinforcement learning](https://md.research.elamur.ai/free/en/papers/le-2022-coderl-mastering-code-generation-through/). In Advances in Neural Information Processing Systems, volume 35, pages 21314–21328. Curran Associates, Inc.
16. Zekun Li, Zhiyu Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Dong, Adithya Sagar, Xifeng Yan, and Paul Crook. 2024. Large language models as zero-shot dialogue state tracker through function calling. In Proceedings of the 62nd Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Zekun+Li%2C+Zhiyu+Chen%2C+Mike+Ross%2C+Patrick+Huber%2C+Seungwhan+Moon%2C+Zhaojiang+Lin%2C+Xin+Dong%2C+Adithya+Sagar%2C+Xifeng+Yan%2C+and+Paul+Crook%2E+2024%2E+Large+language+models+as+zero%2Dshot+dialogue+state+tracker+thro)
17. Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. 2024. [Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation](https://md.research.elamur.ai/free/en/papers/liu-2023-your-code-generated-chatgpt-really/). Advances in Neural Information Processing Systems, 36.
18. Bo-Ru Lu, Yushi Hu, Hao Cheng, Noah A. Smith, and Mari Ostendorf. 2022. Unsupervised learning of hierarchical conversation structure. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5657–5670, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bo%2DRu+Lu%2C+Yushi+Hu%2C+Hao+Cheng%2C+Noah+A%2E+Smith%2C+and+Mari+Ostendorf%2E+2022%2E+Unsupervised+learning+of+hierarchical+conversation+structure%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNL)
19. Shikib Mehri and Maxine Eskenazi. 2021. Schema-guided paradigm for zero-shot dialog. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 499– 508, Singapore and Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shikib+Mehri+and+Maxine+Eskenazi%2E+2021%2E+Schema%2Dguided+paradigm+for+zero%2Dshot+dialog%2E+In+Proceedings+of+the+22nd+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+and+Dialogue%2C+pages+499%E2%80%93+508%2C+)
20. Johannes EM Mosig, Shikib Mehri, and Thomas Kober. 2020. Star: A schema-guided dialog dataset for transfer learning. arXiv preprint arXiv:2010.11853. — [arXiv:2010.11853](https://arxiv.org/abs/2010.11853) [find](https://scholar.google.com/scholar?q=Johannes+EM+Mosig%2C+Shikib+Mehri%2C+and+Thomas+Kober%2E+2020%2E+Star%3A+A+schema%2Dguided+dialog+dataset+for+transfer+learning%2E+arXiv+preprint+arXiv%3A2010%2E11853%2E+%E2%80%94+%5BarXiv%3A2010%2E11853%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2010%2E11)
21. Tomáš Nekvinda and Ondřej Dušek. 2021. Shades of BLEU, flavours of success: The case of MultiWOZ. In Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021), pages 34–46, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tom%C3%A1%C5%A1+Nekvinda+and+Ondr%CC%8Cej+Du%C5%A1ek%2E+2021%2E+Shades+of+BLEU%2C+flavours+of+success%3A+The+case+of+MultiWOZ%2E+In+Proceedings+of+the+1st+Workshop+on+Natural+Language+Generation%2C+Evaluation%2C+and+Metrics+%28GEM+2021%29)
22. NVIDIA. 2024. Nvidia nemo guardrails, docs.nvidia.com/nemo/guardrails/colang_2/overview .html. Accessed: 2025-05-19. [find](https://scholar.google.com/scholar?q=NVIDIA%2E+2024%2E+Nvidia+nemo+guardrails%2C+docs%2Envidia%2Ecom%2Fnemo%2Fguardrails%2Fcolang%5F2%2Foverview+%2Ehtml%2E+Accessed%3A+2025%2D05%2D19%2E)
23. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, page 311–318, USA. Association for Computational Linguistics.
24. Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, and Jianfeng Gao. 2021. Soloist: Building task bots at scale with transfer learning and machine teaching. Transactions of the Association for Computational Linguistics, 9:807–824. [find](https://scholar.google.com/scholar?q=Baolin+Peng%2C+Chunyuan+Li%2C+Jinchao+Li%2C+Shahin+Shayandeh%2C+Lars+Liden%2C+and+Jianfeng+Gao%2E+2021%2E+Soloist%3A+Building+task+bots+at+scale+with+transfer+learning+and+machine+teaching%2E+Transactions+of+the+Associ)
25. Matt Post. 2018. [A call for clarity in reporting BLEU scores](https://md.research.elamur.ai/free/en/papers/post-2018-call-clarity-reporting-bleu-scores/). In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Belgium, Brussels. Association for Computational Linguistics.
26. Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, and Min Li. 2023. End-to-end task-oriented dialogue: A survey of tasks, methods, and future directions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5925–5941, Singapor… [find](https://scholar.google.com/scholar?q=Libo+Qin%2C+Wenbo+Pan%2C+Qiguang+Chen%2C+Lizi+Liao%2C+Zhou+Yu%2C+Yue+Zhang%2C+Wanxiang+Che%2C+and+Min+Li%2E+2023%2E+End%2Dto%2Dend+task%2Doriented+dialogue%3A+A+survey+of+tasks%2C+methods%2C+and+future+directions%2E+In+Proceedings+o)
27. Traian Rebedea, Razvan Dinu, Makesh Narsimhan Sreedhar, Christopher Parisien, and Jonathan Cohen. 2023. NeMo guardrails: A toolkit for controllable and safe LLM applications with programmable rails. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Dem… [find](https://scholar.google.com/scholar?q=Traian+Rebedea%2C+Razvan+Dinu%2C+Makesh+Narsimhan+Sreedhar%2C+Christopher+Parisien%2C+and+Jonathan+Cohen%2E+2023%2E+NeMo+guardrails%3A+A+toolkit+for+controllable+and+safe+LLM+applications+with+programmable+rails%2E+I)
28. Makesh Narsimhan Sreedhar, Traian Rebedea, and Christopher Parisien. 2024. Unsupervised extraction of dialogue policies from conversations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19029–19045, Miami, Florida, USA. Association for Computational… [find](https://scholar.google.com/scholar?q=Makesh+Narsimhan+Sreedhar%2C+Traian+Rebedea%2C+and+Christopher+Parisien%2E+2024%2E+Unsupervised+extraction+of+dialogue+policies+from+conversations%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+i)
29. Haipeng Sun, Junwei Bao, Youzheng Wu, and Xiaodong He. 2023. Mars: Modeling context & state representations with contrastive learning for end-to-end task-oriented dialog. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11139– 11160, Toronto, Canada. Association for Comp… [find](https://scholar.google.com/scholar?q=Haipeng+Sun%2C+Junwei+Bao%2C+Youzheng+Wu%2C+and+Xiaodong+He%2E+2023%2E+Mars%3A+Modeling+context+%26+state+representations+with+contrastive+learning+for+end%2Dto%2Dend+task%2Doriented+dialog%2E+In+Findings+of+the+Associatio)
30. Shubo Tian, Qiao Jin, Lana Yeganova, Po-Ting Lai, Qingqing Zhu, Xiuying Chen, Yifan Yang, Qingyu Chen, Won Kim, Donald C Comeau, et al. 2024. Opportunities and challenges for chatgpt and large language models in biomedicine and health. Briefings in Bioinformatics, 25(1):bbad493. [find](https://scholar.google.com/scholar?q=Shubo+Tian%2C+Qiao+Jin%2C+Lana+Yeganova%2C+Po%2DTing+Lai%2C+Qingqing+Zhu%2C+Xiuying+Chen%2C+Yifan+Yang%2C+Qingyu+Chen%2C+Won+Kim%2C+Donald+C+Comeau%2C+et+al%2E+2024%2E+Opportunities+and+challenges+for+chatgpt+and+large+languag)
31. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
32. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023. [Large language models as optimizers](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-optimizers/). arXiv preprint arXiv:2309.03409.
33. Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, and James Zou. 2024. [Textgrad: Automatic "differentiation" via text](https://md.research.elamur.ai/free/en/papers/yuksekgonul-2024-textgrad-automatic-differentiation-text/).
34. Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, and Helen Meng. 2023. SGP-TOD: Building task bots effortlessly via schema-guided LLM prompting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13348–13369, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiaoying+Zhang%2C+Baolin+Peng%2C+Kun+Li%2C+Jingyan+Zhou%2C+and+Helen+Meng%2E+2023%2E+SGP%2DTOD%3A+Building+task+bots+effortlessly+via+schema%2Dguided+LLM+prompting%2E+In+Findings+of+the+Association+for+Computational+Ling)
35. Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, and Yonghui Wu. 2023. AnyTOD: A programmable task-oriented dialog system. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16189– 16204, Sin… [find](https://scholar.google.com/scholar?q=Jeffrey+Zhao%2C+Yuan+Cao%2C+Raghav+Gupta%2C+Harrison+Lee%2C+Abhinav+Rastogi%2C+Mingqiu+Wang%2C+Hagen+Soltau%2C+Izhak+Shafran%2C+and+Yonghui+Wu%2E+2023%2E+AnyTOD%3A+A+programmable+task%2Doriented+dialog+system%2E+In+Proceedings)

*Updated 1 November 2026*