# Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs

arXiv: https://arxiv.org/abs/2602.21763 · HTML: https://mlsanity.com/paper/2602.21763/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Are self-explanations from Large Language Models faithful?](https://mlsanity.com/paper/2401.07927/) (2024)
- [NILE : Natural Language Inference with Faithful Natural Language Explanations](https://mlsanity.com/paper/2005.12116/) (2020)
- [Towards Explainable NLP: A Generative Explanation Framework for Text Classification](https://mlsanity.com/paper/1811.00196/) (2018)
- [On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification](https://mlsanity.com/paper/2004.12617/) (2020)
- [Explanation-based Finetuning Makes Models More Robust to Spurious Cues](https://mlsanity.com/paper/2305.04990/) (2023)
- [Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations](https://mlsanity.com/paper/2106.13876/) (2021)
- [DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2305.03973/) (2023)
- [Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations](https://mlsanity.com/paper/2301.02724/) (2023)
- [A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2112.11740/) (2021)
- [From Discourse to Narrative: Knowledge Projection for Event Relation Extraction](https://mlsanity.com/paper/2106.08629/) (2021)
- [Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2210.07032/) (2022)
- [Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation](https://mlsanity.com/paper/2306.06480/) (2023)
- [Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2402.15080/) (2024)
- [Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2211.13873/) (2022)
- [Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference](https://mlsanity.com/paper/1708.01353/) (2017)
- [Discursive Circuits: How Do Language Models Understand Discourse Relations?](https://mlsanity.com/paper/2510.11210/) (2025)
- [A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation](https://mlsanity.com/paper/2301.11749/) (2023)
- [Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2311.00367/) (2023)

## Abstract (arXiv)

Implicit Discourse Relation Recognition (IDRR) remains a challenging task due to the requirement for deep semantic understanding in the absence of explicit discourse markers. A further limitation is that existing methods only predict relations without providing any supporting explanations. Recent advances in large language models (LLMs) have shown strong reasoning capabilities in both deep language understanding and natural language explanation generation. In this work, we propose a simple yet effective approach to distill the reasoning capabilities of LLMs into lightweight IDRR models to improve both performance and interpretability. Specifically, we first prompt an LLM to generate explanations for each training instance conditioned on its gold label. Then, we introduce a novel classification-generation framework that jointly performs relation prediction and explanation generation, and train it with the additional supervision of LLM-generated explanations. Our framework is plug-and-play, enabling easy integration with most existing IDRR models. Experimental results on PDTB demonstrate that our approach significantly improves IDRR performance, while human evaluation further confirms that the generated explanations enhance model interpretability. Furthermore, we validate the generality of our approach on sentiment classification and natural language inference