新研究探索用于LLM推理的交互式可视化和因果归因

报道来源 [4]

1. arXiv cs.CL TIER_1 English(EN) · Kaviraj Pather, Elena Hadjigeorgiou, Arben Krasniqi, Claire Schmit, Irina Rusu, Marc Pons, Kabir Khan · 2026-06-26 04:00

   Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning

   arXiv:2509.01412v3 Announce Type: replace Abstract: Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugging, and control difficult in high-stakes settings. We present Vis-CoT, a human-…

2. arXiv cs.AI TIER_1 English(EN) · Jun Zhao · 2026-06-21 15:59

   轻巧观察，深度思考：多模态思维链推理能做什么，不能做什么

   Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks remains unclear. In this paper, we aim to systematically investigate the key ques…

3. Hugging Face Daily Papers TIER_1 English(EN) · 2026-06-21 00:00

   Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

   Multimodal Chain-of-Thought reasoning shows selective effectiveness across different tasks, with limitations in maintaining visual introspection during reasoning processes.

4. arXiv cs.CL TIER_1 English(EN) · Radu Marinescu · 2026-06-20 01:18

   Chain-of-Thought推理的局部因果归因

   Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In this work, we take a local approach toward this goal by analyzing the causal relationships among individual components, termed unit…