LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback (2024.acl-long)
Copied to clipboard
| Challenge: | Creating trusted and safe online spaces for people with different backgrounds and opinions is a challenge for social media platforms. |
| Approach: | They propose a reinforcement learning-based rewriting approach that balances content preservation and appropriateness based on existing classifiers. |
| Outcome: | The proposed approach significantly outperforms baselines including few-shot learning, prompting, and humans. |
Similar Papers
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. |
Can LLMs Clarify? Investigation and Enhancement of Large Language Models on Argument Claim Optimization (2025.coling-main)
Copied to clipboard
| Challenge: | While Large Language Models (LLMs) have demonstrated proficiency in text rewriting tasks such as style transfer and query rewrite, their application to claim optimization remains unexplored. |
| Approach: | They propose to use a sliding window mechanism to evaluate the performance of large language models in claim clarification tasks under different settings. |
| Outcome: | The proposed model improves the performance of three LLMs on the claim clarification task under zero-shot, few-shot and supervised fine-tuning settings. |
Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms (2025.acl-long)
Copied to clipboard
| Challenge: | Social media platforms use machine learning and artificial intelligence to maximize user engagement, but can indirectly cause exposure to harmful content. |
| Approach: | They propose a re-ranking approach using Large Language Models to assess and rerank content sequences using large annotated data sets. |
| Outcome: | The proposed method significantly outperforms existing proprietary moderation methods on three datasets, three models and across three configurations. |
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting (2025.findings-naacl)
Copied to clipboard
Mohamed Salim Aissi, Clément Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud, Laure Soulier, Nicolas Thome
| Challenge: | Reinforcement learning (RL) is a promising approach for aligning large language models knowledge with sequential decision-making tasks. |
| Approach: | They propose to use a contrastive loss framework to analyze the sensitivity of LLMs to prompt formulations following RL training in a textual environment. |
| Outcome: | The proposed framework improves the model's robustness and generalization capabilities by minimizing the model’s internal representations and salient tokens. |
Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have significantly improved text comprehension. |
| Approach: | They propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection that leverages contextual learning to understand and apply instructions to new scenarios without additional training. |
| Outcome: | The proposed framework outperforms existing models on three EDOS tasks and scores 0.8681 on binary sexism detection, 0.6829 on category classification of sexists and 0.4722 on task C. |
Inverse Reinforcement Learning Meets Large Language Model Alignment (2025.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial will provide a comprehensive review of recent advances in LLM alignment . it will highlight the necessity of constructing neural reward models from human data . |
| Approach: | This tutorial will provide a comprehensive review of recent advances in LLM alignment through the lens of inverse reinforcement learning. |
| Outcome: | This tutorial will provide a comprehensive review of recent advances in LLM alignment through the lens of inverse reinforcement learning (IRL). |
Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing reinforcement learning methods do not provide fine-grained supervision for complex reasoning tasks. |
| Approach: | They propose a reinforcement learning method that incorporates a generative model as the reward model and a token-level supervision model for RL training. |
| Outcome: | Experiments on 8 tasks show the proposed method is effective . |
CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Argument Improvement (ArgImp) is a text rewriting task that requires LLMs to shorten texts while increasing word length and merging sentences. |
| Approach: | They propose to use a pipeline to evaluate LLMs' behavior in a text rewriting setting . they use four linguistic levels to examine the qualities of argumentative texts . |
| Outcome: | The proposed evaluation pipeline compares LLMs on argumentative texts and their improvement on a broad set of argumentation corpora. |
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have shown a powerful ability for text generation, but undesired behaviors such as toxicity and hallucinations can manifest. |
| Approach: | They propose to formalize text generation as a future-constrained generation problem to minimize undesirable behaviors and enforce faithfulness to instructions. |
| Outcome: | The proposed approach is effective across three tasks, including keyword-constrained generation, toxicity reduction, and factual correctness in question-answering. |
Argument Quality Assessment in the Age of Instruction-Following Large Language Models (2024.lrec-main)
Copied to clipboard
Henning Wachsmuth, Gabriella Lapesa, Elena Cabrio, Anne Lauscher, Joonsuk Park, Eva Maria Vecchi, Serena Villata, Timon Ziegenbein
| Challenge: | Argument quality assessment is critical for opinion formation, decision making, writing education, and the like. |
| Approach: | They propose to use large language models to leverage knowledge across contexts to enable a much more reliable assessment. |
| Outcome: | The proposed approach improves the quality of argumentation and the ability to leverage knowledge across contexts. |