Papers with reinforcement learning approach
Integrating Question Rewrites in Conversational Question Answering: A Reinforcement Learning Approach (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing approaches to improve QR performance dependencies among dialogue history dependencies are limited. |
| Approach: | They propose a reinforcement learning approach that integrates QR and CQA tasks without corresponding labeled QR datasets. |
| Outcome: | The proposed approach improves existing pipeline approaches in conversational question answering (QA) existing methods depend on assumption of corresponding QR datasets for every CQA dataset, resulting in poor performance. |
Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods use contrastive learning (CL) to learn effective sentence representations, but require extensive human annotation. |
| Approach: | They propose a reinforcement learning approach for fine-tuning small-parameter LLMs to generate high-quality hard contrastive data without human feedback. |
| Outcome: | The proposed method achieves state-of-the-art on seven semantic text similarity tasks. |
Multi-Reward Reinforced Summarization with Saliency and Entailment (N18-2)
Copied to clipboard
| Challenge: | Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy. |
| Approach: | They propose a novel reward function for ROUGESal and Entail to improve abstractive summarization . they use a coverage-based reward function to combine ROUGE and En Tail . |
| Outcome: | The proposed method achieves state-of-the-art results on CNN/Daily Mail dataset and strong improvements in a test-only transfer setup on DUC-2002. |
Combining Cognitive Modeling and Reinforcement Learning for Clarification in Dialogue (2020.coling-main)
Copied to clipboard
| Challenge: | In many domains, dialogue systems need to work collaboratively with users to reconstruct meaning . this requires a system that can give targeted, effective feedback about the system’s understanding . |
| Approach: | They propose a system that collaborates on reference tasks that distinguish arbitrarily varying color patches from similar distractors and use crowd workers to test their approach. |
| Outcome: | The proposed system can distinguish varying color patches from distractors and elicit correct answers that the system understands. |
LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification (D19-1)
Copied to clipboard
| Challenge: | Existing text classification models are fragile and sensitive to simple perturbations. |
| Approach: | They propose a generator-classifier adversarial training approach to improve classification models . they use a large-scale lexical knowledge base to generate attacking examples . |
| Outcome: | The proposed approach outperforms strong baselines and reduces test errors on neural networks. |
Table-R1: Region-based Reinforcement Learning for Table Understanding (2026.findings-acl)
Copied to clipboard
Zhenhe Wu, Jian Yang, Zhongjiang He, Changzai Pan, Jiaheng Liu, Xianjie Wu, Yu Zhao, Shuangyong Song, Yongxiang Li, Zhoujun Li, Xuelong Li
| Challenge: | Tables are a widely used data format that poses unique challenges for language models due to their structured row-column interactions. |
| Approach: | They propose a region-based reinforcement learning approach that integrates region evidence into reasoning steps. |
| Outcome: | The proposed method outperforms baseline models on three benchmark datasets and significantly reduces the reasoning token consumption by 67.5%. |
Training Language Models to Use Prolog as a Tool (2026.findings-acl)
Copied to clipboard
| Challenge: | Language models often produce plausible but incorrect reasoning traces that are difficult to verify. |
| Approach: | They train language models to use Prolog as an external symbolic reasoning tool . they find an accuracy–auditability trade-off between tuning for correctness alone and using Prolog only for the final computation . |
| Outcome: | The proposed model outperforms supervised fine-tuning on a clean version of GSM8K. |
Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Comparing human-like edits to LLMs, we observe a mismatch in editing strategies. |
| Approach: | They propose a reinforcement learning approach that teaches LLMs human-like editing to improve the appropriateness of arguments. |
| Outcome: | The proposed approach outperforms baselines and the state of the art in human-like editing, with multi-round editing achieving appropriateness close to full rewriting. |