A Nash Equilibrium Framework For Training-Free Multimodal Step Verification

• URL: http://arxiv.org/abs/2605.20033v1
• Date: Tue, 19 May 2026 15:54:22 GMT
• Title: A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
• Abstract summary: We propose a training-free verification approach that treats step-wise verification as a coordination problem among specialized judges.<n>Our approach achieves consistent improvements of 2.4% to 5.2% over baseline models.
• Score: 36.36755437383068
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Learned critics need extensive labeled data and show inconsistent performance across different tasks. Meanwhile, existing training-free methods simply average scores from different sources, missing a key insight: when these scores disagree, that disagreement itself carries important information about whether a reasoning step is truly valid or not. We propose a training-free verification approach that treats step-wise verification as a coordination problem among specialized judges. We formalize these judges' interaction as a Nash equilibrium game where agreement signals valid steps while disagreement reveals instability. Our method computes equilibrium scores through a closed-form solution, enabling both disagreement-aware filtering and stability-conscious ranking of reasoning steps. Evaluated across six benchmarks, our approach achieves consistent improvements of 2.4% to 5.2% over baseline models and shows competitive performance against learned critics, demonstrating that cross-modal agreement (not just average confidence) provides robust verification signals without task-specific adaptation.

Related papers

• VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus [15.909063535182632]
  Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers.<n>We formalise this as a coupled scoring problem among disparate, frozen verifiers.<n>We propose a training-free domain-agnostic step-wise verification approach we call VERDICT: VERification via Disagreement-Informed Coupled Thresholding.
  arXiv  Detail & Related papers  (2026-08-11T08:46:38Z)
• Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty [5.839104770457067]
  Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently.<n>We propose structural uncertainty, a consistency-aware framework derived from the stability of self-preference-induced rankings.
  arXiv  Detail & Related papers  (2026-06-15T21:39:47Z)
• A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs [3.4007995136788]
  Layer-contrast decoding, inference-time intervention, and learned logit adapters have demonstrated 10-30 point gains on TruthfulQA.<n>Modern instruction-tuned LLMs already achieve substantially higher baselines.<n> Deliberative prompting methods appear more robust in the evaluated regime.
  arXiv  Detail & Related papers  (2026-06-10T14:48:05Z)
• Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution [12.955460962298588]
  We introduce Stepwise Confidence Attribution (SCA), a framework for closed-source LLMs that assigns step-level confidence based only on generated reasoning traces.<n>SCA reliably identifies low-confidence steps strongly correlated with reasoning errors.<n>Using step-level confidence to guide self-correction improves the correction success rate by up to 13.5% over answer-level feedback.
  arXiv  Detail & Related papers  (2026-05-19T00:57:51Z)
• Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning [28.00739954235118]
  We introduce Ranking-Aware (RAC), a training-time framework that supervises confidence using two comparison signals.<n>We instantiate RAC on Qwen2.5-VL InternVL-3.5 backbones and evaluate on six multimodal reasoning benchmarks under clean and corrupted inputs.
  arXiv  Detail & Related papers  (2026-05-16T13:51:29Z)
• Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning [8.024041325202612]
  Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths.<n>We introduce a conformal procedure for CoT reasoning that directly addresses aggregation uncertainty.<n>Our approach replaces majority voting with weighted score aggregation over reasoning paths and calibrates an abstention rule using conformal risk control.
  arXiv  Detail & Related papers  (2026-05-13T20:33:59Z)
• CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution [52.691495954442985]
  CoVerRL is a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other.<n> Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks.<n>Self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
  arXiv  Detail & Related papers  (2026-03-18T14:38:55Z)
• Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation [3.23600523782706]
  We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning.<n>We propose two complementary metrics: Match F1, which scores step-level precision and recall via semantic similarity matching, and Ordered Match F1, which penalizes disordered reasoning chains.<n>CPR-Curriculum achieves a 32% improvement in Match F1 via GRPO where additive reward strategies fail, improving reasoning without manual step annotation.
  arXiv  Detail & Related papers  (2026-03-13T15:48:15Z)
• Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know" [47.930782177987446]
  Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations.<n>We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks.<n>Because factual knowledge is stable while hallucinations are agreement, cross-regime provides a precise signal of internal uncertainty.
  arXiv  Detail & Related papers  (2026-02-04T18:39:58Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.