mlsanityData to 14 Oct 2026

DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics

arXiv 2407.06426 ↗First posted 8 Jul 2024cs.CL cs.AI cs.MAcited by 14

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs) by having multiple agents discuss solutions to a problem over several rounds of debate. However, models often generate incorrect yet confident-sounding responses, which can mislead others. This issue arises partly because agents do not consider how confident their peers are. To address this, we propose DebUnc, a debate framework that uses uncertainty metrics to assess agent confidence. Confidence is then conveyed through a modified attention mechanism that adjusts token weights, or through textual prompts. Evaluations across benchmarks show that attention-based methods are particularly effective and that performance continues to improve as uncertainty estimation becomes more reliable. The code is available at https://github.com/lukeyoffe/debunc.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 33 of its 47 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

33 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View3 Oct
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2017Deep reinforcement learning from human preferencescited by 3,912
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  12. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
19 more
  1. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  2. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  3. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  4. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 445
  5. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  6. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  7. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
  8. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  9. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  10. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  11. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  12. 2024To Believe or Not to Believe Your LLMcited by 120
  13. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 105
  14. 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 91
  15. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 81
  16. 2024Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden Statescited by 52
  17. 2023Let Models Speak Ciphers: Multiagent Debate through Embeddingscited by 51
  18. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 44
  19. 2024Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Frameworkcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 6.

14 papers.

Sort:

By area:

  1. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 58
  2. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 36
  3. 2025OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaborationcited by 30
  4. 2025Thought Communication in Multiagent Collaborationcited by 30
  5. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunitiescited by 20
  6. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversitycited by 18
  7. 2024Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Modelscited by 14
  8. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systemscited by 8
  9. 2025MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Mediacited by 4
  10. 2026Uncertainty Propagation in LLM-Based Systemscited by 3
  11. 2026When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systemscited by 2
  12. 2025Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safetycited by 0
2 more
  1. 2026Confidence Composition for Multiagent Language Model Systemscited by 0
  2. 2026Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study
  2. 2025Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
  3. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  4. 2025Enhancing Multi-Agent Debate System Performance via Confidence Expression
  5. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
  6. 2026AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
  7. 2026DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles
  8. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs