English
Related papers

Related papers: RL4F: Generating Natural Language Feedback with Re…

200 papers

Large language models (LLMs) have been widely used for various tasks and applications. However, LLMs and fine-tuning are limited to the pre-trained data. For example, ChatGPT's world knowledge until 2021 can be outdated or inaccurate. To…

Computation and Language · Computer Science 2025-04-24 Ahsan Bilal , Beiyu Lin

We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework.…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever…

Computation and Language · Computer Science 2025-01-31 Yiteng Tu , Weihang Su , Yujia Zhou , Yiqun Liu , Qingyao Ai

In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tuning (SFT) methods, although efficient in training, have…

Computation and Language · Computer Science 2025-09-17 Min Zeng , Jingfei Sun , Xueyou Luo , Caiquan Liu , Shiqi Zhang , Li Xie , Xiaoxin Chen

Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…

Machine Learning · Computer Science 2025-06-26 Yanzhi Zhang , Zhaoxi Zhang , Haoxiang Guan , Yilin Cheng , Yitong Duan , Chen Wang , Yue Wang , Shuxin Zheng , Jiyan He

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this…

Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of…

Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired…

Machine Learning · Computer Science 2024-01-03 Qianxi Li , Yingyue Cao , Jikun Kang , Tianpei Yang , Xi Chen , Jun Jin , Matthew E. Taylor

Systematic reviews are vital for guiding practice, research, and policy, yet they are often slow and labour-intensive. Large language models (LLMs) could offer a way to speed up and automate systematic reviews, but their performance in such…

Computation and Language · Computer Science 2024-04-11 Qusai Khraisha , Sophie Put , Johanna Kappenberg , Azza Warraitch , Kristin Hadfield

Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality…

Computation and Language · Computer Science 2024-03-20 Xingyao Wang , Hao Peng , Reyhaneh Jabbarvand , Heng Ji

Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and…

Software Engineering · Computer Science 2025-06-03 Manav Nitin Kapadnis , Atharva Naik , Carolyn Rose

Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by training with only first-order rollout (generating multiple…

Computation and Language · Computer Science 2026-02-27 Zhe Yang , Yudong Wang , Rang Li , Zhifang Sui

Training Large Language Models (LLMs) with Reinforcement Learning from AI Feedback (RLAIF) aligns model outputs more closely with human preferences. This involves an evaluator model ranking multiple candidate responses to user prompts.…

Computation and Language · Computer Science 2024-06-04 Peter Devine

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

Aim. There are 10s of thousands of code review comments each week at Meta. We developed Metamate for Code Review (MetaMateCR) that provides AI-assisted fixes for reviewer comments in production at scale. Method. We developed an internal…

Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style…

With the rapid advancement of Large Language Models (LLMs), developing effective critic modules for precise guidance has become crucial yet challenging. In this paper, we initially demonstrate that supervised fine-tuning for building critic…

Computation and Language · Computer Science 2025-07-22 Qiaoyu Tang , Hao Xiang , Le Yu , Bowen Yu , Hongyu Lin , Yaojie Lu , Xianpei Han , Le Sun , Junyang Lin

Generative AI and large language models hold great promise in enhancing programming education by generating individualized feedback and hints for learners. Recent works have primarily focused on improving the quality of generated feedback…

Machine Learning · Computer Science 2025-03-10 Nachiket Kotalwar , Alkis Gotovos , Adish Singla

State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement…

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical…

Computation and Language · Computer Science 2023-03-10 Baolin Peng , Michel Galley , Pengcheng He , Hao Cheng , Yujia Xie , Yu Hu , Qiuyuan Huang , Lars Liden , Zhou Yu , Weizhu Chen , Jianfeng Gao
‹ Prev 1 3 4 5 6 7 10 Next ›