REVIEW 8 cited by
DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
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.
Forward citations
Cited by 8 Pith papers
-
Experience-Calibrated Contrastive Decoding for Mitigating Hallucinations in LM-Based Text-to-Speech
Experience-Calibrated Contrastive Decoding, a training-free decoding method that strengthens text alignment signals, reduces speech hallucination errors across four LM-based TTS models and nine languages.
-
MigrationBench: Repository-Level Code Migration Benchmark from Java 8
MigrationBench provides 5,102 real Maven repositories as a Java 8 to Java 17 migration benchmark, plus an evaluation framework and an LLM feedback agent that achieves 62.33% minimal and 27.33% maximal migration succes...
-
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
A new open-source library and benchmark, xRouteBench, evaluates LLM routers on a shared cost-aware protocol across text, memory, vision, time-series, and personalized tasks.
-
Estimating LLM Uncertainty with Evidence
LogTokU splits token uncertainty into aleatoric and epistemic components from the top-K logits, enabling single-pass hallucination detection and uncertainty-guided decoding.
-
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
OSC uses learned Collaborator Knowledge Models and RL-trained communication policies to make LLM agents communicate adaptively, claiming gains on AlpacaEval 2.0 and MT-Bench.
-
CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate
CortexDebate prunes the multi-agent debate graph every round using a McKinsey-style trust score per directed link, reporting accuracy gains over full-debate baselines on eight datasets with shorter per-agent contexts.
-
A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.
-
Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models
The paper claims that injecting ERNIE as a fourth agent with a hand-set confidence weight into a Debunc-style debate system raises Arithmetic accuracy to 0.940, above prior baselines.
Discussion (0). Continue with ORCID to comment.