# LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction

arXiv: https://arxiv.org/abs/2607.23420 · HTML: https://mlsanity.com/paper/2607.23420/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [A Frustratingly Easy Approach for Entity and Relation Extraction](https://mlsanity.com/paper/2010.12812/) (2020)
- [C-ICL: Contrastive In-context Learning for Information Extraction](https://mlsanity.com/paper/2402.11254/) (2024)
- [SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents](https://mlsanity.com/paper/2410.21155/) (2024)
- [CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation](https://mlsanity.com/paper/2210.07022/) (2022)
- [mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning](https://mlsanity.com/paper/2308.09073/) (2023)
- [Distinguishing Ignorance from Error in LLM Hallucinations](https://mlsanity.com/paper/2410.22071/) (2024)
- [Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks](https://mlsanity.com/paper/2310.17238/) (2023)
- [Aligning Visual Contrastive learning models via Preference Optimization](https://mlsanity.com/paper/2411.08923/) (2024)
- [Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R2)GRPO](https://mlsanity.com/paper/2505.22068/) (2025)

## Built on by (most cited first, 1 of 1)

- [Calibrated Typed Decisions for Entity, Relation, and Event Extraction](https://mlsanity.com/paper/2610.17113/) (2026)

## Abstract (arXiv)

Large language models show strong promise for information extraction (IE), but existing reflection-based correction methods are often misaligned with structured extraction outputs. Free-form self-reflection can flag an error, yet it rarely identifies whether the failure is a missing span, wrong label, boundary mismatch, invalid relation type, or reversed argument order. We introduce LA-RL (Label-Aware Reflective Reinforcement Learning), an outcome-supervised framework that guides IE self-correction with task-grounded diagnostic labels. A single backbone first predicts an extraction, diagnoses task-specific error labels, and then revises its output conditioned on the diagnosis. Training starts from diagnostic data labeled by an annotation model for cold-start supervised fine-tuning and proceeds through two GRPO stages that reward final extraction quality, format validity, and first-pass correctness, without a process reward model. Experiments on named entity recognition, relation extraction, and event extraction show consistent same-backbone gains over SFT, including 6.83 average F1 on SciER relation extraction, about 20 F1 on out-of-distribution relation extraction, and 14.80 trigger F1 plus 17.50 argument F1 on DuEE1.0. Ablations show that reflection structure is task-sensitive: stronger constraints benefit relation extraction, whereas named entity recognition needs less restrictive correction under domain shift.