paper-with-me

홈 › Papers

The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction

2025-10-07 · Xinyu Guo, Zhengliang Shi, Minglai Yang, Mihai Surdeanu arxiv

Despite the remarkable reasoning capabilities of large language models, they still struggle with one-shot relation extraction without predefined relation labels. We identify two pitfalls: models are often misled by irrelevant tokens instead of relation-conveying semantics, and they often fail to align with the abstraction level human annotators expect. We introduce a novel framework that closes this gap with two components: (1) COGRE, a cognitively-inspired reasoning framework that structures RE into a series of processes mimicking human text-processing; and (2) HIT@DICT, a reinforcement learning intermediate reward strategy that encourages reasoning to align with relational labels by rewarding relation-relevant phrases in reasoning. The reward is derived on a credit dictionary automatically extracted from correct predictions. Our experiments show that our framework improves both accuracy and explanation quality by addressing these two pitfalls. For example, COGRE with Qwen2.5-14B-Instruct on One-shot NYT29 achieves 24.65% F1, surpassing prior reasoning-based designs. Optimizing this approach with RL using HIT@DICT further improves performance by +23.46% points. Finally, human evaluation shows that our best model generates relational phrases closely aligned with gold labels, increasing human explanation quality ratings by 54% (relative).

📄 PDF Abstract BibTeX arXiv:2510.06198

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningRelation Extraction

Similar Papers 제목 키워드 기반

LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning

2026-07-15 · Qiang Zhu, Jiajun Wu, Longyi Wang arxiv

Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LOTAPO , a self-generated…

Reinforcement Learning

MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation

2026-05-26 · Haoyu Zheng, Yun Zhu, Shu Yuan, Shangming Chen 외 arxiv

Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to s…

DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

2017-10-31 · ICLR 2018 1 · Caiming Xiong, Victor Zhong, Richard Socher

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed …

Question Answering

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

2024-06-06 · Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue 외

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g.,…

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

2026-06-25 · Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar, Rao Muhammad Anwer 외 arxiv

Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and self-consistency reward schemes in existin…

Visual Question AnsweringImage CaptioningVisual Reasoning