paper-with-me

Papers

Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty

2026-01-17 · Murilo da Luz, Bruno Brandão, Luana Martins, Gustavo Oliveira, Bryan de Oliveira, Luckeciano Melo, Telma Soares arxiv

The use of Large Language Models (LLMs) for reasoning and planning tasks has drawn increasing attention in Artificial Intelligence research. Despite their remarkable progress, these models still exhibit limitations in multi-step inference scenarios, particularly in mathematical and logical reasoning. We introduce PREGU (Partial Reasoning Guided by Uncertainty). PREGU monitors the entropy of the output distribution during autoregressive generation and halts the process whenever entropy exceeds a defined threshold, signaling uncertainty. From that point, a localized search is performed in the latent space to refine the partial reasoning and select the most coherent answer, using the Soft Reasoning method. Experiments conducted with LLaMA-3-8B, Mistral-7B, and Qwen2-7B across four reasoning benchmarks (GSM8K, GSM-Hard, SVAMP, and StrategyQA) showed performance greater than or similar to Soft Reasoning, indicating that entropy can serve as an effective signal to trigger selective refinement during reasoning.

📄 PDF Abstract BibTeX arXiv:2601.12040

Code (0)

등록된 구현이 없습니다.

Tasks

Logical Reasoning

Similar Papers 제목 키워드 기반

TGPR: Tree-Guided Policy Refinement for Robust Self-Debugging of LLMs

2025-10-08 · Daria Ozerova, Ekaterina Trofimova arxiv

Iterative refinement has been a promising paradigm to enable large language models (LLMs) to resolve difficult reasoning and problem-solving tasks. One of the key challenges, however, is how to effectively search through…

Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement

2026-06-28 · Aunabil Chakma, Mihai Surdeanu, Eduardo Blanco arxiv

Automatic prompt optimization is still underexplored for episodic few-shot relation extraction with smaller language models. We propose a two-stage framework that combines reasoning-based prompt optimization with gradien…

Relation Extraction

DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS

2025-08-01 · Yingxu Wang, Shiqi Fan, Mengzhu Wang, Siyang Gao 외 arxiv

Knowledge Graph Question Answering (KGQA) aims to interpret natural language queries and perform structured reasoning over knowledge graphs by leveraging their relational and semantic structures to retrieve accurate answ…

Natural Language QueriesGraph Question AnsweringKnowledge Graphs

Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning

2026-08-21 · Haonan Jia, Shichao Dong, Zenghui Sun, Jiawen Zheng 외 arxiv

Reinforcement Learning (RL) has demonstrated significant gains in image captioning, yet it is still limited in encouraging Large Vision-Language Models (LVLMs) to explore novel reasoning strategies. This limitation leads…

Reinforcement LearningImage Captioning

Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs

2025-10-23 · Tristan Cinquin, Geoff Pleiss, Agustinus Kristiadi arxiv

While chain-of-thought prompting with Best-of-N (BoN) selection has become popular for mathematical reasoning in large language models (LLMs), its linear structure fails to capture the branching and exploratory nature of…

Mathematical Reasoning