---
title: "Truth or Sophistry? LoFa — paper by Shen et al. (2026)"
description: "The proposed LFR@k metric separates real reasoning failures from questions the model never knew. 33 references."
authors: ["Xudong Shen", "li Yuan", "Ye Chen", "Xin Wu", "Yi Cai", "Zhiyong 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.1112/"
doi: "10.18653/v1/2026.acl-long.1112"
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/shen-2026-truth-or-sophistry-lofa-benchmark/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shen-2026-truth-or-sophistry-lofa-benchmark/)

[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/46/) / Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies

# Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies

**Authors:** Xudong Shen, [li Yuan](https://md.research.elamur.ai/free/en/authors/li-yuan/), [Ye Chen](https://md.research.elamur.ai/free/en/authors/ye-chen/), [Xin Wu](https://md.research.elamur.ai/free/en/authors/xin-wu/), [Yi Cai](https://md.research.elamur.ai/free/en/authors/yi-cai/) and [Zhiyong Wu](https://md.research.elamur.ai/free/en/authors/zhiyong-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.1112/) · [PDF](https://aclanthology.org/2026.acl-long.1112.pdf) · [DOI 10.18653/v1/2026.acl-long.1112](https://doi.org/10.18653/v1/2026.acl-long.1112) · [OpenAlex](https://openalex.org/W7166826360)

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

## Summary
Most research on LLMs and logical fallacies tests whether models can name or classify a flawed argument. This paper asks a different question: can a model hold onto a correct answer when someone pushes fallacious reasoning at it? Earlier debate-style studies such as LOGICOM used contested opinion topics, so a model changing its stance could not be counted as an error. LoFa avoids this by building every item on a factual question with one verifiable answer, adapted from the Farm dataset, whose questions come from Wikipedia-based QA sources.

A multi-agent pipeline generates persuasive arguments for a false claim across 10 fallacy types. Models first pass screening stages and then face a multi-round debate. The proposed LFR@k metric separates real reasoning failures from questions the model never knew.

The experiments show that resistance depends on model scale, architecture, and fallacy type. Models generally withstand arguments with flawed evidence but often give in to distraction or distortion tactics. The benchmark therefore turns persuasion-induced errors into something that can be measured, which matters for building trustworthy assistants.

## Key points
- **Dataset:** about 2000 items covering 10 fallacies, grouped into two categories.
  - Distraction/Distortion: Straw Man, Equivocation, Ad Hominem, False Cause, Red Herring.
  - Flaws in Reasoning/Evidence: Hasty Generalization, Slippery Slope, False Dilemma, Appeal to Authority, Circular Reasoning.
  - Sources: Natural Questions, TruthfulQA and BoolQ, taken via Farm and standardized to an MCQ format.
- **Model vulnerabilities:** Llama-series models are especially weak against Distraction/Distortion fallacies. Strong closed-source models show notable deference to Appeal to Authority.
- **Chain-of-Thought prompting on GPT-4 (NQ1):** average LFR@3 rose by roughly 7–13% for most fallacy types, with the largest gain of 13.16% on Straw Man. Appeal to Authority was the exception, dropping by 1.87%.
- **Interpretability analysis:** a LogicLens study of Llama-3.1-8b-instruct shows the predictions in layers 20–25 collapsing toward null tokens like "None". After that point, the model settles on the fallacious answer.
- **Availability and limitations:** data and code are released at github.com/xdshen-ai/LoFa. The authors acknowledge three limitations: the benchmark is modest in size, only dense decoder-only models were tested, and the explanation of architectural effects is limited.

*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

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 333 works · 87,019 citations
- [Tsinghua Shenzhen International Graduate School](https://md.research.elamur.ai/free/en/universities/tsinghua-shenzhen-international-graduate-school/) — University, Shenzhen, China · 28 works · 3,035 citations
- [South China University of Technology](https://md.research.elamur.ai/free/en/universities/south-china-university-of-technology/) — University, Guangzhou, China · 22 works · 1,554 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 (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works

## Cite

Cite as: Xudong Shen, li Yuan, Ye Chen, Xin Wu, Yi Cai and Zhiyong Wu. 2026. Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies. 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{shen2026truth,
  title = {{Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies}},
  author = {Xudong Shen, li Yuan, Ye Chen, Xin Wu, Yi Cai and Zhiyong 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.1112},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1112}
}
```

- [← previous Truth or Dare: Analyzing LLM Susceptibility to External Evidence of Varying Factuality](https://md.research.elamur.ai/free/en/papers/su-2026-truth-or-dare-analyzing-llm/)
- [next → TruthSplit: Operationalizing Conditional Validity in Arguments Through Multi-Perspective Reasoning](https://md.research.elamur.ai/free/en/papers/stieger-2026-truthsplit-operationalizing-conditional-validity-arguments/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/)

## References

33 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rehab Mohamed Ahmed Abd-Eldayem. 2023. The relationship between cognitive bias and logical fallacies in egyptian society. Social Sciences, 12(6):281–293. [find](https://scholar.google.com/scholar?q=Rehab+Mohamed+Ahmed+Abd%2DEldayem%2E+2023%2E+The+relationship+between+cognitive+bias+and+logical+fallacies+in+egyptian+society%2E+Social+Sciences%2C+12%286%29%3A281%E2%80%93293%2E)
2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
3. Bo Bennett. 2012. Logically fallacious: the ultimate collection of over 300 logical fallacies (Academic Edition). eBookIt. com. [find](https://scholar.google.com/scholar?q=Bo+Bennett%2E+2012%2E+Logically+fallacious%3A+the+ultimate+collection+of+over+300+logical+fallacies+%28Academic+Edition%29%2E+eBookIt%2E+com%2E)
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 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.
5. Fengxiang Cheng, Haoxuan Li, Fenrong Liu, Robert van Rooij, Kun Zhang, and Zhouchen Lin. 2025a. Empowering llms with logical reasoning: A comprehensive survey. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, pages 10400–10408. International Jo… [find](https://scholar.google.com/scholar?q=Fengxiang+Cheng%2C+Haoxuan+Li%2C+Fenrong+Liu%2C+Robert+van+Rooij%2C+Kun+Zhang%2C+and+Zhouchen+Lin%2E+2025a%2E+Empowering+llms+with+logical+reasoning%3A+A+comprehensive+survey%2E+In+Proceedings+of+the+Thirty%2DFourth+Inte)
6. Keyuan Cheng, Xudong Shen, Yihao Yang, Tengyue Wang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, and Di Wang. 2025b. CODEMENV: Benchmarking large language models on code migration. In Findings of the Association for Computational Linguistics: ACL 2025, pages 2719–2744, Vienna, Austria. Assoc… [find](https://scholar.google.com/scholar?q=Keyuan+Cheng%2C+Xudong+Shen%2C+Yihao+Yang%2C+Tengyue+Wang%2C+Yang+Cao%2C+Muhammad+Asif+Ali%2C+Hanbin+Wang%2C+Lijie+Hu%2C+and+Di+Wang%2E+2025b%2E+CODEMENV%3A+Benchmarking+large+language+models+on+code+migration%2E+In+Findings)
7. Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. 2019. [BoolQ: Exploring the surprising difficulty of natural yes/no questions](https://md.research.elamur.ai/free/en/papers/clark-2019-boolq-exploring-surprising-difficulty-natural/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:…
8. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
9. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
10. Ivan Habernal, Raffael Hannemann, Christian Pollak, Christopher Klamm, Patrick Pauli, and Iryna Gurevych. 2017. Argotario: Computational argumentation meets serious games. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 7–12, Co… [find](https://scholar.google.com/scholar?q=Ivan+Habernal%2C+Raffael+Hannemann%2C+Christian+Pollak%2C+Christopher+Klamm%2C+Patrick+Pauli%2C+and+Iryna+Gurevych%2E+2017%2E+Argotario%3A+Computational+argumentation+meets+serious+games%2E+In+Proceedings+of+the+2017+C)
11. Chadi Helwe, Tom Calamai, Pierre-Henri Paris, Chloé Clavel, and Fabian Suchanek. 2024. MAFALDA: A benchmark and comprehensive study of fallacy detection and classification. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Lan… [find](https://scholar.google.com/scholar?q=Chadi+Helwe%2C+Tom+Calamai%2C+Pierre%2DHenri+Paris%2C+Chlo%C3%A9+Clavel%2C+and+Fabian+Suchanek%2E+2024%2E+MAFALDA%3A+A+benchmark+and+comprehensive+study+of+fallacy+detection+and+classification%2E+In+Proceedings+of+the+2024+)
12. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, and 1 others. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Lin…
13. Woojin Lee, Jaewook Lee, and Harksoo Kim. 2024. Logic: Llm-originated guidance for internal cognitive improvement of small language models in stance detection. PeerJ Computer Science, 10:e2585. [find](https://scholar.google.com/scholar?q=Woojin+Lee%2C+Jaewook+Lee%2C+and+Harksoo+Kim%2E+2024%2E+Logic%3A+Llm%2Doriginated+guidance+for+internal+cognitive+improvement+of+small+language+models+in+stance+detection%2E+PeerJ+Computer+Science%2C+10%3Ae2585%2E)
14. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. [TruthfulQA: Measuring how models mimic human falsehoods](https://md.research.elamur.ai/free/en/papers/lin-2022-truthfulqa-measuring-how-models-mimic/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252, Dublin, Ireland. Association for Computational Linguistics…
15. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, and 1 others. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=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+and+1+others%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412)
16. Hanmeng Liu, Zhizhang Fu, Mengru Ding, Ruoxi Ning, Chaoli Zhang, Xiaozhang Liu, and Yue Zhang. 2025. Logical reasoning in [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). Preprint, arXiv:2502.09100.
17. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang 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 Natural L…
18. Luca Mouchel, Debjit Paul, Shaobo Cui, Robert West, Antoine Bosselut, and Boi Faltings. 2025. A logical fallacy-informed framework for argument generation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Te… [find](https://scholar.google.com/scholar?q=Luca+Mouchel%2C+Debjit+Paul%2C+Shaobo+Cui%2C+Robert+West%2C+Antoine+Bosselut%2C+and+Boi+Faltings%2E+2025%2E+A+logical+fallacy%2Dinformed+framework+for+argument+generation%2E+In+Proceedings+of+the+2025+Conference+of+the)
19. Mihir Parmar, Nisarg Patel, Neeraj Varshney, Mutsumi Nakamura, Man Luo, Santosh Mashetty, Arindam Mitra, and Chitta Baral. 2024. [LogicBench: Towards systematic evaluation of logical reasoning ability of large language models](https://md.research.elamur.ai/free/en/papers/parmar-2024-logicbench-systematic-evaluation-logical-reasoning/). In Proceedings of the 62nd Annual Meeting of the Association for Computati…
20. Amirreza Payandeh, Dan Pluth, Jordan Hosier, Xuesu Xiao, and Vijay K. Gurbani. 2024. How susceptible are LLMs to logical fallacies? In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8276–8286, Torino, I… [find](https://scholar.google.com/scholar?q=Amirreza+Payandeh%2C+Dan+Pluth%2C+Jordan+Hosier%2C+Xuesu+Xiao%2C+and+Vijay+K%2E+Gurbani%2E+2024%2E+How+susceptible+are+LLMs+to+logical+fallacies%3F+In+Proceedings+of+the+2024+Joint+International+Conference+on+Computa)
21. Domina Petric. 2020. Logical fallacies. On-line Article (preprint), doi, 10. [find](https://scholar.google.com/scholar?q=Domina+Petric%2E+2020%2E+Logical+fallacies%2E+On%2Dline+Article+%28preprint%29%2C+doi%2C+10%2E)
22. Robert B Ricco. 2007. Individual differences in the analysis of informal reasoning fallacies. Contemporary Educational Psychology, 32(3):459–484. [find](https://scholar.google.com/scholar?q=Robert+B+Ricco%2E+2007%2E+Individual+differences+in+the+analysis+of+informal+reasoning+fallacies%2E+Contemporary+Educational+Psychology%2C+32%283%29%3A459%E2%80%93484%2E)
23. Irfan Robbani, Paul Reisert, Naoya Inoue, Surawat Pothong, Camélia Guerraoui, Wenzhi Wang, Shoichi Naito, Jungmin Choi, and Kentaro Inui. 2024. Flee the flaw: Annotating the underlying logic of fallacious arguments through templates and slot-filling. Preprint, arXiv:2406.12402. [find](https://scholar.google.com/scholar?q=Irfan+Robbani%2C+Paul+Reisert%2C+Naoya+Inoue%2C+Surawat+Pothong%2C+Cam%C3%A9lia+Guerraoui%2C+Wenzhi+Wang%2C+Shoichi+Naito%2C+Jungmin+Choi%2C+and+Kentaro+Inui%2E+2024%2E+Flee+the+flaw%3A+Annotating+the+underlying+logic+of+fallac)
24. Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande, Himanshu Rawlani, Filip Ilievski, Hông-Ân Sandlin, and Alain Mermoud. 2023. [Robust and explainable identification of logical fallacies in natural language arguments](https://md.research.elamur.ai/free/en/papers/zou-2023-universal-transferable-adversarial-attacks-aligned/). Knowledge-Based Systems, 266:110418. and transferable adversarial…
25. Yiyi Tao, Yixian Shen, Hang Zhang, Yanxin Shen, Lun Wang, Chuanqi Shi, and Shaoshuai Du. 2024. Robustness of large language models against adversarial attacks. In 2024 4th International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC), pages 182–185. IEEE. [find](https://scholar.google.com/scholar?q=Yiyi+Tao%2C+Yixian+Shen%2C+Hang+Zhang%2C+Yanxin+Shen%2C+Lun+Wang%2C+Chuanqi+Shi%2C+and+Shaoshuai+Du%2E+2024%2E+Robustness+of+large+language+models+against+adversarial+attacks%2E+In+2024+4th+International+Conference+on+)
26. Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023. [Jailbroken: how does llm safety training fail?](https://md.research.elamur.ai/free/en/papers/wei-2023-jailbroken-llm-safety-training-fail/) In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY, USA. Curran Associates Inc.
27. Yuan Xia, Akanksha Atrey, Fadoua Khmaissia, and Kedar S Namjoshi. 2025. Can large language models learn formal logic? a data-driven training and evaluation framework. arXiv preprint arXiv:2504.20213. — [arXiv:2504.20213](https://arxiv.org/abs/2504.20213) [find](https://scholar.google.com/scholar?q=Yuan+Xia%2C+Akanksha+Atrey%2C+Fadoua+Khmaissia%2C+and+Kedar+S+Namjoshi%2E+2025%2E+Can+large+language+models+learn+formal+logic%3F+a+data%2Ddriven+training+and+evaluation+framework%2E+arXiv+preprint+arXiv%3A2504%2E20213%2E+)
28. Rongwu Xu, Brian Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi, Tianwei Zhang, Zhixuan Fang, Wei Xu, and Han Qiu. 2024. The earth is flat because...: Investigating LLMs’ belief towards misinformation via persuasive conversation. In Proceedings of the 62nd Annual Meeting of the Association for Computat… [find](https://scholar.google.com/scholar?q=Rongwu+Xu%2C+Brian+Lin%2C+Shujian+Yang%2C+Tianqi+Zhang%2C+Weiyan+Shi%2C+Tianwei+Zhang%2C+Zhixuan+Fang%2C+Wei+Xu%2C+and+Han+Qiu%2E+2024%2E+The+earth+is+flat+because%2E%2E%2E%3A+Investigating+LLMs%E2%80%99+belief+towards+misinformation+vi)
29. Li Yuan, Yi Cai, Xudong Shen, Qing Li, Qingbao Huang, Zikun Deng, and Tao Wang. 2025. Collaborative multi-lora experts with achievement-based multi-tasks loss for unified multimodal information extraction. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence,… [find](https://scholar.google.com/scholar?q=Li+Yuan%2C+Yi+Cai%2C+Xudong+Shen%2C+Qing+Li%2C+Qingbao+Huang%2C+Zikun+Deng%2C+and+Tao+Wang%2E+2025%2E+Collaborative+multi%2Dlora+experts+with+achievement%2Dbased+multi%2Dtasks+loss+for+unified+multimodal+information+extrac)
30. Li Yuan, Qingfei Huang, Bingshan Zhu, Yi Cai, Qingbao Huang, Changmeng Zheng, Zikun Deng, and Tao Wang. 2026. Hybrid-dmkg: A hybrid reasoning framework over dynamic multimodal knowledge graphs for multimodal multihop qa with knowledge editing. In Proceedings of the AAAI Conference on Artificial Inte… [find](https://scholar.google.com/scholar?q=Li+Yuan%2C+Qingfei+Huang%2C+Bingshan+Zhu%2C+Yi+Cai%2C+Qingbao+Huang%2C+Changmeng+Zheng%2C+Zikun+Deng%2C+and+Tao+Wang%2E+2026%2E+Hybrid%2Ddmkg%3A+A+hybrid+reasoning+framework+over+dynamic+multimodal+knowledge+graphs+for+mul)
31. Jian Zhang, Zhangqi Wang, Haiping Zhu, Kangda Cheng, Kai He, Bo Li, Qika Lin, Jun Liu, and Erik Cambria. 2026a. Mars: Multi-agent adaptive reasoning with socratic guidance for automated prompt optimization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19):16307–16315. [find](https://scholar.google.com/scholar?q=Jian+Zhang%2C+Zhangqi+Wang%2C+Haiping+Zhu%2C+Kangda+Cheng%2C+Kai+He%2C+Bo+Li%2C+Qika+Lin%2C+Jun+Liu%2C+and+Erik+Cambria%2E+2026a%2E+Mars%3A+Multi%2Dagent+adaptive+reasoning+with+socratic+guidance+for+automated+prompt+optimiz)
32. Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Fangzhi Xu, Qika Lin, Lingling Zhang, Rui Mao, Erik Cambria, and Jun Liu. 2026b. Maps: Multi-agent personality shaping for collaborative reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19):16316– 16324. [find](https://scholar.google.com/scholar?q=Jian+Zhang%2C+Zhiyuan+Wang%2C+Zhangqi+Wang%2C+Fangzhi+Xu%2C+Qika+Lin%2C+Lingling+Zhang%2C+Rui+Mao%2C+Erik+Cambria%2C+and+Jun+Liu%2E+2026b%2E+Maps%3A+Multi%2Dagent+personality+shaping+for+collaborative+reasoning%2E+Proceedings+)
33. Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, and Matt Fredrikson. 2023. Universal [find](https://scholar.google.com/scholar?q=Andy+Zou%2C+Zifan+Wang%2C+Nicholas+Carlini%2C+Milad+Nasr%2C+J%2E+Zico+Kolter%2C+and+Matt+Fredrikson%2E+2023%2E+Universal)

*Updated 1 November 2026*