paper-with-me

Papers

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

2025-08-29 · Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li, Tong Yu, Xiang Chen, Ritwik Sinha, Jingbo Shang, Julian McAuley arxiv

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles of reasoning steps and their transitions remain underexplored. In this paper, we introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics. Specifically, to capture the evolving semantics of CoT reasoning, each reasoning step is represented via spectral analysis of token-level embeddings and clustered into semantically coherent latent states. To characterize the global structure of reasoning, we model their progression as a Markov chain, yielding a structured and interpretable view of the reasoning process. This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.

📄 PDF Abstract BibTeX arXiv:2509.00190

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoning

2025-11-15 · Shaowei Guan, Yu Zhai, Zhengyu Zhang, Yanze Wang 외 arxiv

Large Language Models (LLMs) are increasingly vulnerable to adversarial attacks that can subtly manipulate their outputs. While various defense mechanisms have been proposed, many operate as black boxes, lacking transpar…

Adversarial Defense

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

2022-01-28 · Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 외

We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reason…

Common Sense ReasoningGSM8KLanguage ModelingLanguage Modelling+2

X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning

2025-09-25 · Prasanna Reddy Pulakurthi, Jiamian Wang, Majid Rabbani, Sohail Dianat 외 arxiv

Prevalent text-to-video retrieval systems mainly adopt embedding models for feature extraction and compute cosine similarities for ranking. However, this design presents two limitations. Low-quality text-video data pairs…

Video Retrieval

A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning

2024-06-18 · Lijie Hu, Liang Liu, Shu Yang, Xin Chen 외

Chain-of-Thought (CoT) holds a significant place in augmenting the reasoning performance for large language models (LLMs). While some studies focus on improving CoT accuracy through methods like retrieval enhancement, ye…

Retrieval

MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering

2025-10-26 · Hai-Dang Nguyen, Minh-Anh Dang, Minh-Tan Le, Minh-Tuan Le arxiv

Explainability is critical for the clinical adoption of medical visual question answering (VQA) systems, as physicians require transparent reasoning to trust AI-generated diagnoses. We present MedXplain-VQA, a comprehens…

Visual Question Answering