paper-with-me

Papers

Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages

2025-12-27 · Anaelia Ovalle, Candace Ross, Sebastian Ruder, Adina Williams, Karen Ullrich, Mark Ibrahim, Levent Sagun arxiv

Large language models demonstrate strong reasoning capabilities through chain-of-thought prompting, but whether this reasoning quality transfers across languages remains underexplored. We introduce a human-validated framework to evaluate whether model-generated reasoning traces logically support their conclusions across languages. Analyzing 65k reasoning traces from GlobalMMLU questions across 6 languages and 6 frontier models, we uncover a critical blind spot: while models achieve high task accuracy, their reasoning can fail to support their conclusions. Reasoning traces in non-Latin scripts show at least twice as much misalignment between their reasoning and conclusions than those in Latin scripts. We develop an error taxonomy through human annotation to characterize these failures, finding they stem primarily from evidential errors (unsupported claims, ambiguous facts) followed by illogical reasoning steps. Our findings demonstrate that current multilingual evaluation practices provide an incomplete picture of model reasoning capabilities and highlight the need for reasoning-aware evaluation frameworks.

📄 PDF Abstract BibTeX arXiv:2512.22712

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering

2025-08-04 · Ziruo Yi, Jinyu Liu, Ting Xiao, Mark V. Albert arxiv

Radiology visual question answering (RVQA) provides precise answers to questions about chest X-ray images, alleviating radiologists' workload. While recent methods based on multimodal large language models (MLLMs) and re…

Visual Question AnsweringMultimodal Reasoning

Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning

2026-06-14 · Zhenyu Yu arxiv

Instruction-tuned language models can answer the same causal-reasoning question differently after its English variable names are replaced by type-preserving placeholders, although the structural causal model and the gold…

Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models

2025-10-11 · Minbin Huang, Runhui Huang, Chuanyang Zheng, Jingyao Li 외 arxiv

Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by directly optimizing correctness, rather than r…

Reinforcement Learning

How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA

2026-07-17 · Navya Gupta, Bingjie Xu, Avinash Anand, Timothy Liu 외 arxiv

Compositional visual question answering requires Vision-Language Models (VLMs) to execute multiple reasoning operations like object selection, spatial relation resolution, and attribute verification. Despite strong aggre…

Visual Question AnsweringAttribute ExtractionVisual Grounding

CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making

2025-06-15 · Songtao Jiang, YuAn Wang, Ruizhe Chen, Yan Zhang 외

In medical visual question answering (Med-VQA), achieving accurate responses relies on three critical steps: precise perception of medical imaging data, logical reasoning grounded in visual input and textual questions, a…

Answer GenerationDecision MakingLogical ReasoningMedical Visual Question Answering+4