# Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R2)GRPO

arXiv: https://arxiv.org/abs/2505.22068 · HTML: https://mlsanity.com/paper/2505.22068/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [Empirical Study of Zero-Shot NER with ChatGPT](https://mlsanity.com/paper/2310.10035/) (2023)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://mlsanity.com/paper/2304.05454/) (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)
- [Revisiting Large Language Models as Zero-shot Relation Extractors](https://mlsanity.com/paper/2310.05028/) (2023)
- [SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents](https://mlsanity.com/paper/2410.21155/) (2024)
- [UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction](https://mlsanity.com/paper/2402.06861/) (2024)
- [Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks](https://mlsanity.com/paper/2310.17238/) (2023)
- [PIVOINE: Instruction Tuning for Open-world Information Extraction](https://mlsanity.com/paper/2305.14898/) (2023)

## Built on by (most cited first, 2 of 2)

- [LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction](https://mlsanity.com/paper/2607.23420/) (2026)
- [Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction](https://mlsanity.com/paper/2605.04221/) (2026)

## Abstract (arXiv)

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while supervised-finetuning(SFT) with distillation can. We study this from the view of Scientific information extraction (SciIE) where LLMs and reasoning LLMs underperforms small Bert-based models. SciIE require both the reasoning and memorization. We argue that both SFT and RLVR can refine the reasoning path and improve reasoning capacity in a simple way based on SciIE. We propose two-stage training with 1. MimicSFT, using structured reasoning templates without needing high-quality chain-of-thought data, 2. R2GRPO with relevance and rule-induced rewards. Experiments on scientific IE benchmarks show that both methods can improve the reasoning capacity. R2GRPO with mimicSFT surpasses baseline LLMs and specialized supervised models in relation extraction. Our code is available at https://github.com/ranlislz/R2GRPO.