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

arXiv: https://arxiv.org/abs/2510.06198 · HTML: https://mlsanity.com/paper/2510.06198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond](https://mlsanity.com/paper/2503.10460/) (2025)
- [Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge](https://mlsanity.com/paper/2501.18099/) (2025)
- [Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum](https://mlsanity.com/paper/2308.14034/) (2023)
- [Instruct and Extract: Instruction Tuning for On-Demand Information Extraction](https://mlsanity.com/paper/2310.16040/) (2023)
- [How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?](https://mlsanity.com/paper/2305.01555/) (2023)
- [Deep Reinforcement Learning for Imbalanced Classification](https://mlsanity.com/paper/1901.01379/) (2019)
- [ADELIE: Aligning Large Language Models on Information Extraction](https://mlsanity.com/paper/2405.05008/) (2024)
- [Think-J: Learning to Think for Generative LLM-as-a-Judge](https://mlsanity.com/paper/2505.14268/) (2025)
- [Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction](https://mlsanity.com/paper/2311.05922/) (2023)
- [Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains](https://mlsanity.com/paper/2501.14431/) (2025)
- [Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers](https://mlsanity.com/paper/2505.19439/) (2025)
- [R1-RE: Cross-Domain Relation Extraction with RLVR](https://mlsanity.com/paper/2507.04642/) (2025)
- [Relation Extraction with Explanation](https://mlsanity.com/paper/2005.14271/) (2020)
- [Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification](https://mlsanity.com/paper/2403.03305/) (2024)
- [It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers](https://mlsanity.com/paper/2204.11424/) (2022)
- [Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL](https://mlsanity.com/paper/2509.06024/) (2025)
- [Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation](https://mlsanity.com/paper/2404.04445/) (2024)

## Abstract (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).