paper-with-me

Papers

Quantifying Cross-Query Contradictions in Multi-Query LLM Reasoning

2026-04-16 · Rohit Kumar Salla, Ramya Manasa Amancherla, Manoj Saravanan arxiv

Large language models frequently produce mutually inconsistent answers when reasoning over multiple related queries. We study case-file logical consistency: maintaining a globally satisfiable belief state across interdependent queries. We introduce a benchmark of 390 multi-query reasoning instances with entailment/contradiction/unknown labels and propose set-level metrics including Case Satisfiability Rate, Contradiction Density and Revision Cost. Our solver-augmented approach extracts commitments, verifies global satisfiability and performs counterexample-guided repair. Across four reasoning domains, our method substantially reduces cross-query contradictions (SetCons: 0.56 to 0.94) while preserving per-query accuracy, demonstrating that global coherence is critical for robust multi-query reasoning.

📄 PDF Abstract BibTeX arXiv:2604.14525

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DiverseAgentEntropy: Quantifying Black-Box LLM Uncertainty through Diverse Perspectives and Multi-Agent Interaction

2024-12-12 · Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao 외

Quantifying the uncertainty in the factual parametric knowledge of Large Language Models (LLMs), especially in a black-box setting, poses a significant challenge. Existing methods, which gauge a model's uncertainty throu…

Investigating Bias in Political Search Query Suggestions by Relative Comparison with LLMs

2024-10-31 · Fabian Haak, Björn Engelmann, Christin Katharina Kreutz, Philipp Schaer

Search query suggestions affect users' interactions with search engines, which then influences the information they encounter. Thus, bias in search query suggestions can lead to exposure to biased search results and can …

Exploring the Nexus Between Retrievability and Query Generation Strategies

2024-04-15 · Aman Sinha, Priyanshu Raj Mall, Dwaipayan Roy

Quantifying bias in retrieval functions through document retrievability scores is vital for assessing recall-oriented retrieval systems. However, many studies investigating retrieval model bias lack validation of their q…

Retrieval

SparseCL: Sparse Contrastive Learning for Contradiction Retrieval

2024-06-15 · Haike Xu, Zongyu Lin, Yizhou Sun, Kai-Wei Chang 외

Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query, which is important to many downstream applications like fact checking and data cleani…

Contrastive LearningFact CheckingRetrievalSentence Embeddings

Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective

2026-05-26 · Xiang Fang, Zeyu Xiong, Wanlong Fang, Xiaoye Qu 외 arxiv

This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstru…

Contrastive Learning