---
title: "AGSC — paper by Luo et al. (2026) — summary and ideas"
description: "This paper targets uncertainty quantification (UQ) for long-form LLM outputs, where hallucinations are… 46 references, cited by 2 papers here."
authors: ["Guanran Luo", "Wentao Qiu", "Wanru Zhao", "Wenhan Lv", "Zhongquan Jian", "Meihong Wang", "Qingqiang Wu"]
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.434/"
doi: "10.18653/v1/2026.acl-long.434"
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/luo-2026-agsc-adaptive-granularity-semantic-clustering/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/luo-2026-agsc-adaptive-granularity-semantic-clustering/)

[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/6/) / AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation

# AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation

**Authors:** [Guanran Luo](https://md.research.elamur.ai/free/en/authors/guanran-luo/), [Wentao Qiu](https://md.research.elamur.ai/free/en/authors/wentao-qiu/), Wanru Zhao, Wenhan Lv, [Zhongquan Jian](https://md.research.elamur.ai/free/en/authors/zhongquan-jian/), [Meihong Wang](https://md.research.elamur.ai/free/en/authors/meihong-wang/) and [Qingqiang Wu](https://md.research.elamur.ai/free/en/authors/qingqiang-wu/) · **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.434/) · [PDF](https://aclanthology.org/2026.acl-long.434.pdf) · [DOI 10.18653/v1/2026.acl-long.434](https://doi.org/10.18653/v1/2026.acl-long.434) · [OpenAlex](https://openalex.org/W7166804948)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/luo-2026-agsc-adaptive-granularity-semantic-clustering/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
This paper targets uncertainty quantification (UQ) for long-form LLM outputs, where hallucinations are hard to detect because one response can mix several topics. Earlier work such as LUQ breaks responses into atomic facts and checks them with NLI against other sampled responses. That approach has three weaknesses: it is computationally costly, it pools all units uniformly, and it simply drops neutral NLI labels. AGSC is a black-box, sampling-based framework with two main ideas. First, it reads neutral NLI predictions as a signal. Using the gap between entailment and contradiction, it decides whether a sentence is off-topic noise to skip or uncertain content to split into atomic facts. Second, it embeds units, reduces them with UMAP, and soft-clusters them with a GMM. This yields theme-aware weights, so minor or off-topic parts count less in the final score. On the BIO (FActScore) and LongFact benchmarks, AGSC reaches state-of-the-art correlation with factuality while cutting inference time by roughly 60%. This makes fine-grained reliability checks more practical.

## Key points
- **Pipeline:**
  - Sample multiple responses and treat the first as the anchor.
  - Score its units with sliding-window NLI against the reference responses, keeping the best-supporting chunk.
  - Renormalize the scores over entailment and contradiction only.
  - Compute uncertainty as one minus the average support.
- **Why neutrality matters:** neutral labels cover 40–70% of sentences. About 30–50% of those lean toward genuine uncertainty. On BIO, raw neutral probabilities saturate above 0.95, which is why AGSC uses the entailment–contradiction gap instead.
- **Efficiency:** AGSC decomposes only about 25% of the candidates that LUQ-Atomic would split. Overall latency drops by about 60% compared with full atomic decomposition.
- **Resources:** Llama-3 and Qwen-2.5 as generators, DeBERTa-v3 (MNLI) for NLI, and GTE embeddings. Code is included in the supplementary materials.
- **Limitations:**
  - Experiments are English-only.
  - The method depends on how well the NLI model is calibrated.
  - Hallucinations repeated consistently across samples go undetected, since the score measures consensus rather than truth.
  - It is poorly suited to math or code outputs.

*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

- [Xiamen University](https://md.research.elamur.ai/free/en/universities/xiamen-university/) — University, Xiamen, China · 24 works · 2,317 citations
- [Minjiang University](https://md.research.elamur.ai/free/en/universities/minjiang-university/) — University, Fuzhou, China · 2 works · 8 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [✍️ Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) · 214 works

## Cite

Cite as: Guanran Luo, Wentao Qiu, Wanru Zhao, Wenhan Lv, Zhongquan Jian, Meihong Wang and Qingqiang Wu. 2026. AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation. 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{luo2026agsc,
  title = {{AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation}},
  author = {Guanran Luo, Wentao Qiu, Wanru Zhao, Wenhan Lv, Zhongquan Jian, Meihong Wang and Qingqiang Wu},
  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.434},
  url = {https://doi.org/10.18653/v1/2026.acl-long.434}
}
```

- [← previous AGS-KSU at QIAS 2026: A Comparative Study of Prompting and LLM Approaches for Structured Islamic Inheritance Reasoning](https://md.research.elamur.ai/free/en/papers/sidaoui-2026-ags-ksu-qias-2026-comparative/)
- [next → AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments](https://md.research.elamur.ai/free/en/papers/vaghefi-2026-ai-climate-finance-agentic-retrieval/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

46 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jinze Bai, Shuai Bai, Yun-Hsuan Sung, Tian-Yi Tang, et al. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609.
2. Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning. Springer, New York, NY, USA. [find](https://scholar.google.com/scholar?q=Christopher+M%2E+Bishop%2E+2006%2E+Pattern+Recognition+and+Machine+Learning%2E+Springer%2C+New+York%2C+NY%2C+USA%2E)
3. Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, et al. 2023. [A survey on evaluation of large language models](https://md.research.elamur.ai/free/en/papers/chang-2023-survey-evaluation-large-language-models/). arXiv preprint arXiv:2307.03109.
4. Armen Der Kiureghian and Ove Ditlevsen. 2009. Aleatory or epistemic? does it matter? Structural Safety, 31(2):105–112. [find](https://scholar.google.com/scholar?q=Armen+Der+Kiureghian+and+Ove+Ditlevsen%2E+2009%2E+Aleatory+or+epistemic%3F+does+it+matter%3F+Structural+Safety%2C+31%282%29%3A105%E2%80%93112%2E)
5. Jinhao Duan, Hao Cheng, Shiqi Wang, Chenan Wang, Alex Zavalny, Renjing Xu, Bhavya Kailkhura, and Kaidi Xu. 2023. Shifting attention to relevance: Towards the uncertainty estimation of large language models. arXiv preprint arXiv:2307.01379. [find](https://scholar.google.com/scholar?q=Jinhao+Duan%2C+Hao+Cheng%2C+Shiqi+Wang%2C+Chenan+Wang%2C+Alex+Zavalny%2C+Renjing+Xu%2C+Bhavya+Kailkhura%2C+and+Kaidi+Xu%2E+2023%2E+Shifting+attention+to+relevance%3A+Towards+the+uncertainty+estimation+of+large+language+m)
6. Jinhao Duan, Hao Cheng, Shiqi Wang, Alex Zavalny, Chenan Wang, Renjing Xu, Bhavya Kailkhura, and Kaidi Xu. 2024. Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language models. In Proceedings of the 62nd Annual Meeting of the Association for Com… [find](https://scholar.google.com/scholar?q=Jinhao+Duan%2C+Hao+Cheng%2C+Shiqi+Wang%2C+Alex+Zavalny%2C+Chenan+Wang%2C+Renjing+Xu%2C+Bhavya+Kailkhura%2C+and+Kaidi+Xu%2E+2024%2E+Shifting+attention+to+relevance%3A+Towards+the+predictive+uncertainty+quantification+of+f)
7. Xiang Gao, Jiaxin Zhang, Lalla Mouatadid, and Kamalika Das. 2024. SPUQ: Perturbation-based uncertainty quantification for large language models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). [find](https://scholar.google.com/scholar?q=Xiang+Gao%2C+Jiaxin+Zhang%2C+Lalla+Mouatadid%2C+and+Kamalika+Das%2E+2024%2E+SPUQ%3A+Perturbation%2Dbased+uncertainty+quantification+for+large+language+models%2E+In+Proceedings+of+the+18th+Conference+of+the+European+C)
8. Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, et al. 2023. A survey of uncertainty in deep neural networks. Artificial Intelligence Review, 56(Suppl 1):1513–1589. [find](https://scholar.google.com/scholar?q=Jakob+Gawlikowski%2C+Cedrique+Rovile+Njieutcheu+Tassi%2C+Mohsin+Ali%2C+Jongseok+Lee%2C+Matthias+Humt%2C+et+al%2E+2023%2E+A+survey+of+uncertainty+in+deep+neural+networks%2E+Artificial+Intelligence+Review%2C+56%28Suppl+1%29%3A)
9. Yonatan Geifman and Ran El-Yaniv. 2017. Selective classification for deep neural networks. In Advances in Neural Information Processing Systems, volume 30, pages 4878–4887. [find](https://scholar.google.com/scholar?q=Yonatan+Geifman+and+Ran+El%2DYaniv%2E+2017%2E+Selective+classification+for+deep+neural+networks%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+30%2C+pages+4878%E2%80%934887%2E)
10. Andrey Malinin and Mark J. F. Gales. 2021. Uncertainty estimation in autoregressive structured prediction. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Andrey+Malinin+and+Mark+J%2E+F%2E+Gales%2E+2021%2E+Uncertainty+estimation+in+autoregressive+structured+prediction%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
11. Jiahui Geng, Fengyu Cai, Yuxia Wang, Heinz Koeppl, Preslav Nakov, and Iryna Gurevych. 2023. [A survey of language model confidence estimation and calibration](https://md.research.elamur.ai/free/en/papers/geng-2023-survey-confidence-estimation-calibration-large/). arXiv preprint arXiv:2311.08298.
12. Potsawee Manakul, Adian Liusie, and Mark J. F. Gales. 2023. SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9004–9017, Singapore. Association for Compu… [find](https://scholar.google.com/scholar?q=Potsawee+Manakul%2C+Adian+Liusie%2C+and+Mark+J%2E+F%2E+Gales%2E+2023%2E+SelfCheckGPT%3A+Zero%2Dresource+black%2Dbox+hallucination+detection+for+generative+large+language+models%2E+In+Proceedings+of+the+2023+Conference+on)
13. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. [DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/). arXiv preprint arXiv:2111.09543.
14. Dan Hendrycks and Kevin Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Dan+Hendrycks+and+Kevin+Gimpel%2E+2017%2E+A+baseline+for+detecting+misclassified+and+out%2Dof%2Ddistribution+examples+in+neural+networks%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
15. Stephen C. Hora. 1996. Aleatory and epistemic uncertainty in probability elicitation with an example from hazardous waste management. Reliability Engineering & System Safety, 54(2–3):217–223. [find](https://scholar.google.com/scholar?q=Stephen+C%2E+Hora%2E+1996%2E+Aleatory+and+epistemic+uncertainty+in+probability+elicitation+with+an+example+from+hazardous+waste+management%2E+Reliability+Engineering+%26+System+Safety%2C+54%282%E2%80%933%29%3A217%E2%80%93223%2E)
16. Yuheng Huang, Jiayang Song, Zhijie Wang, Huaming Chen, and Lei Ma. 2023. Look before you leap: An exploratory study of uncertainty measurement for large language models. arXiv preprint arXiv:2307.10236. — [arXiv:2307.10236](https://arxiv.org/abs/2307.10236) [find](https://scholar.google.com/scholar?q=Yuheng+Huang%2C+Jiayang+Song%2C+Zhijie+Wang%2C+Huaming+Chen%2C+and+Lei+Ma%2E+2023%2E+Look+before+you+leap%3A+An+exploratory+study+of+uncertainty+measurement+for+large+language+models%2E+arXiv+preprint+arXiv%3A2307%2E1023)
17. Eyke Hüllermeier and Willem Waegeman. 2021. Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods. Machine Learning, 110:457–506. [find](https://scholar.google.com/scholar?q=Eyke+H%C3%BCllermeier+and+Willem+Waegeman%2E+2021%2E+Aleatoric+and+epistemic+uncertainty+in+machine+learning%3A+An+introduction+to+concepts+and+methods%2E+Machine+Learning%2C+110%3A457%E2%80%93506%2E)
18. Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. [Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation](https://md.research.elamur.ai/free/en/papers/kuhn-2023-semantic-uncertainty-linguistic-invariances-uncertainty/). arXiv preprint arXiv:2302.09664.
19. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. [Towards general text embeddings with multi-stage contrastive learning](https://md.research.elamur.ai/free/en/papers/li-2023-towards-general-text-embeddings-multi/). arXiv preprint arXiv:2308.03281.
20. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. Teaching models to express their uncertainty in words. arXiv preprint arXiv:2205.14334. [find](https://scholar.google.com/scholar?q=Stephanie+Lin%2C+Jacob+Hilton%2C+and+Owain+Evans%2E+2022%2E+Teaching+models+to+express+their+uncertainty+in+words%2E+arXiv+preprint+arXiv%3A2205%2E14334%2E)
21. Leland McInnes, John Healy, Nathaniel Saul, and Lukas Gros̈berger. 2018. Umap: Uniform manifold approximation and projection. Journal of Open Source Software, 3(29):861. [find](https://scholar.google.com/scholar?q=Leland+McInnes%2C+John+Healy%2C+Nathaniel+Saul%2C+and+Lukas+Gros%CC%88berger%2E+2018%2E+Umap%3A+Uniform+manifold+approximation+and+projection%2E+Journal+of+Open+Source+Software%2C+3%2829%29%3A861%2E)
22. Meta AI. 2024. Introducing the Llama 3 family of models. [https://ai.meta.com/blog/](https://ai.meta.com/blog/) meta-llama-3/. Meta AI Blog. [↗](https://ai.meta.com/blog/)
23. Sabrina J. Mielke, Arthur Szlam, Emily Dinan, and Y-Lan Boureau. 2022. Reducing conversational agents’ overconfidence through linguistic calibration. Transactions of the Association for Computational Linguistics, 10:857–872. [find](https://scholar.google.com/scholar?q=Sabrina+J%2E+Mielke%2C+Arthur+Szlam%2C+Emily+Dinan%2C+and+Y%2DLan+Boureau%2E+2022%2E+Reducing+conversational+agents%E2%80%99+overconfidence+through+linguistic+calibration%2E+Transactions+of+the+Association+for+Computational+)
24. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. [FActScore: Fine-grained atomic evaluation of factual precision in long form text generation](https://md.research.elamur.ai/free/en/papers/min-2023-factscore-fine-grained-atomic-evaluation/). In Proceedings of the 2023 Conference on Empirical Methods in Natur…
25. Vladislav Nikitin, Jannik Kossen, and Yarin Gal. 2024. Kernel language entropy: Fine-grained uncertainty quantification for LLMs from semantic similarities. In Advances in Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Vladislav+Nikitin%2C+Jannik+Kossen%2C+and+Yarin+Gal%2E+2024%2E+Kernel+language+entropy%3A+Fine%2Dgrained+uncertainty+quantification+for+LLMs+from+semantic+similarities%2E+In+Advances+in+Neural+Information+Processin)
26. OpenAI. 2025. Introducing GPT-4.1 in the API. [https://openai.com/index/gpt-4-1/](https://openai.com/index/gpt-4-1/). OpenAI Blog, published 2025-04-14, accessed 2025-12-17. [↗](https://openai.com/index/gpt-4-1/)
27. Patrick Schober, Christa Boer, and Lothar A Schwarte. 2018. Correlation coefficients: Appropriate use and interpretation. Anesthesia & Analgesia, 126(5):1763– 1768. [find](https://scholar.google.com/scholar?q=Patrick+Schober%2C+Christa+Boer%2C+and+Lothar+A+Schwarte%2E+2018%2E+Correlation+coefficients%3A+Appropriate+use+and+interpretation%2E+Anesthesia+%26+Analgesia%2C+126%285%29%3A1763%E2%80%93+1768%2E)
28. Zhen Lin, Shubhendu Trivedi, and Jimeng Sun. 2024. Generating with confidence: Uncertainty quantification for black-box large language models. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Zhen+Lin%2C+Shubhendu+Trivedi%2C+and+Jimeng+Sun%2E+2024%2E+Generating+with+confidence%3A+Uncertainty+quantification+for+black%2Dbox+large+language+models%2E+Transactions+on+Machine+Learning+Research%2E)
29. Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D Manning, and Chelsea Finn. 2023. Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5433–5442. [find](https://scholar.google.com/scholar?q=Katherine+Tian%2C+Eric+Mitchell%2C+Huaxiu+Yao%2C+Christopher+D+Manning%2C+and+Chelsea+Finn%2E+2023%2E+Just+ask+for+calibration%3A+Strategies+for+eliciting+calibrated+confidence+scores+from+language+models%2E+In+Proce)
30. Chen Ling, Xujiang Zhao, Jiaying Lu, Chengyuan Deng, Can Zheng, Junxiang Wang, Tan Tan, Xiaoqiang Huang, Wei Xu, and Haifeng Chen. 2024. Uncertainty quantification for in-context learning of large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association… [find](https://scholar.google.com/scholar?q=Chen+Ling%2C+Xujiang+Zhao%2C+Jiaying+Lu%2C+Chengyuan+Deng%2C+Can+Zheng%2C+Junxiang+Wang%2C+Tan+Tan%2C+Xiaoqiang+Huang%2C+Wei+Xu%2C+and+Haifeng+Chen%2E+2024%2E+Uncertainty+quantification+for+in%2Dcontext+learning+of+large+lan)
31. Lifu Tu, Rui Meng, Shafiq Joty, Yingbo Zhou, and Semih Yavuz. 2025. Investigating factuality in long-form text generation: The roles of self-known and self-unknownan. In Proceedings of the 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025), pages 322–336, Suzhou, China. Association for Computa… [find](https://scholar.google.com/scholar?q=Lifu+Tu%2C+Rui+Meng%2C+Shafiq+Joty%2C+Yingbo+Zhou%2C+and+Semih+Yavuz%2E+2025%2E+Investigating+factuality+in+long%2Dform+text+generation%3A+The+roles+of+self%2Dknown+and+self%2Dunknownan%2E+In+Proceedings+of+the+2nd+Worksho)
32. Artem Vazhentsev, Ekaterina Fadeeva, Rui Xing, Gleb Kuzmin, Ivan Lazichny, Alexander Panchenko, Preslav Nakov, Timothy Baldwin, Maxim Panov, and Artem Shelmanov. 2025. [Unconditional truthfulness: Learning unconditional uncertainty of large language models](https://md.research.elamur.ai/free/en/papers/vazhentsev-2025-unconditional-truthfulness-learning-unconditional-uncertainty/). In Proceedings of the 2025 Conference on Em…
33. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2024b. Adacomp: Extractive context compression with adaptive predictor for retrieval-augmented large language models. arXiv preprint arXiv:2409.01579. — [arXiv:2409.01579](https://arxiv.org/abs/2409.01579) [find](https://scholar.google.com/scholar?q=Qianchi+Zhang%2C+Hainan+Zhang%2C+Liang+Pang%2C+Hongwei+Zheng%2C+and+Zhiming+Zheng%2E+2024b%2E+Adacomp%3A+Extractive+context+compression+with+adaptive+predictor+for+retrieval%2Daugmented+large+language+models%2E+arXiv+p)
34. Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao, Fuli Feng, Xiangnan He, and Tat-Seng Chua. 2025. Think-while-generating: On-the-fly reasoning for personalized long-form generation. arXiv preprint arXiv:2512.06690. — [arXiv:2512.06690](https://arxiv.org/abs/2512.06690) [find](https://scholar.google.com/scholar?q=Chengbing+Wang%2C+Yang+Zhang%2C+Wenjie+Wang%2C+Xiaoyan+Zhao%2C+Fuli+Feng%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2025%2E+Think%2Dwhile%2Dgenerating%3A+On%2Dthe%2Dfly+reasoning+for+personalized+long%2Dform+generation%2E+arXiv+prepri)
35. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2026. [Stable-rag: Mitigating retrieval-permutation-induced hallucinations in retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/zhang-2026-stable-rag-mitigating-retrieval-permutation/). arXiv preprint arXiv:2601.02993.
36. Chengbing Wang, Wuqiang Zheng, Yang Zhang, Fengbin Zhu, Junyi Cheng, Yi Xie, Wenjie Wang, and Fuli Feng. 2026. [Perm: Psychology-grounded empathetic reward modeling for large language models](https://md.research.elamur.ai/free/en/papers/wang-2026-perm-psychology-grounded-empathetic-reward/). arXiv preprint arXiv:2601.10532.
37. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, et al. 2023. [Siren’s song in the ai ocean: A survey on hallucination in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2023-siren-s-song-ai-ocean/). arXiv preprint arXiv:2309.01219.
38. Cunxiang Wang, Xiaoze Liu, Yuanhao Yue, Xiangru Tang, Tianhang Zhang, Cheng Ji, et al. 2023. [Survey on factuality in large language models: Knowledge, retrieval and domain-specificity](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-factuality-large-language-models/). arXiv preprint arXiv:2309.05660.
39. Jerry Wei, Chengrun Yang, Xinying Song, Yifeng Lu, Nathan Hu, Jie Huang, Dustin Tran, Daiyi Peng, Ruibo Liu, Da Huang, Cosmo Du, and Quoc V. Le. 2024. [Long-form factuality in large language models](https://md.research.elamur.ai/free/en/papers/wei-2024-long-form-factuality-large-language/). In Advances in Neural Information Processing Systems, volume 37, pages 80756–80827. Curran Associates,…
40. Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2022. Uncertainty quantification with pre-trained language models: A large-scale empirical analysis. Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7273– 7284. [find](https://scholar.google.com/scholar?q=Yuxin+Xiao%2C+Paul+Pu+Liang%2C+Umang+Bhatt%2C+Willie+Neiswanger%2C+Ruslan+Salakhutdinov%2C+and+Louis%2DPhilippe+Morency%2E+2022%2E+Uncertainty+quantification+with+pre%2Dtrained+language+models%3A+A+large%2Dscale+empirical+)
41. Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, and Bryan Hooi. 2023. Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms. arXiv preprint arXiv:2310.04937. [find](https://scholar.google.com/scholar?q=Miao+Xiong%2C+Zhiyuan+Hu%2C+Xinyang+Lu%2C+Yifei+Li%2C+Jie+Fu%2C+Junxian+He%2C+and+Bryan+Hooi%2E+2023%2E+Can+llms+express+their+uncertainty%3F+an+empirical+evaluation+of+confidence+elicitation+in+llms%2E+arXiv+preprint+ar)
42. Yingqing Yuan, Linwei Tao, Haohui Lu, et al. 2025. KG-UQ: Knowledge graph-based uncertainty quantification for long text in large language models. In Companion Proceedings of the ACM Web Conference (WWW). [find](https://scholar.google.com/scholar?q=Yingqing+Yuan%2C+Linwei+Tao%2C+Haohui+Lu%2C+et+al%2E+2025%2E+KG%2DUQ%3A+Knowledge+graph%2Dbased+uncertainty+quantification+for+long+text+in+large+language+models%2E+In+Companion+Proceedings+of+the+ACM+Web+Conference+%28W)
43. Caiqi Zhang, Fangyu Liu, Marco Basaldella, and Nigel Collier. 2024a. [LUQ: Long-text uncertainty quantification for LLMs](https://md.research.elamur.ai/free/en/papers/zhang-2024-luq-long-text-uncertainty-quantification/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
44. Qianchi Zhang, Hainan Zhang, Liang Pang, Yongxin Tong, Hongwei Zheng, and Zhiming Zheng. 2025. [find](https://scholar.google.com/scholar?q=Qianchi+Zhang%2C+Hainan+Zhang%2C+Liang+Pang%2C+Yongxin+Tong%2C+Hongwei+Zheng%2C+and+Zhiming+Zheng%2E+2025%2E)
45. Less is more: Compact clue selection for efficient retrieval-augmented generation reasoning. arXiv preprint arXiv:2502.11811. — [arXiv:2502.11811](https://arxiv.org/abs/2502.11811) [find](https://scholar.google.com/scholar?q=Less+is+more%3A+Compact+clue+selection+for+efficient+retrieval%2Daugmented+generation+reasoning%2E+arXiv+preprint+arXiv%3A2502%2E11811%2E+%E2%80%94+%5BarXiv%3A2502%2E11811%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E11811%29)
46. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, et al. 2023. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223.

*Updated 2 November 2026*