ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models

• URL: http://arxiv.org/abs/2505.11010v2
• Date: Fri, 04 Jul 2025 12:51:51 GMT
• Title: ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models
• Authors: Jiangxu Wu, Cong Wang, TianHuang Su, Jun Yang, Haozhi Lin, Chao Zhang, Ming Peng, Kai Shi, SongPan Yang, BinQing Pan, ZiXian Li, Ni Yang, ZhenYu Yang,
• Abstract summary: Existing methods for generating multi-turn dialogue data struggle to ensure both diversity and quality in instructions.<n>We propose Review-Instruct, a novel framework that synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process.
• Score: 9.660334829409253
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The effectiveness of large language models (LLMs) in conversational AI is hindered by their reliance on single-turn supervised fine-tuning (SFT) data, which limits contextual coherence in multi-turn dialogues. Existing methods for generating multi-turn dialogue data struggle to ensure both diversity and quality in instructions. To address this, we propose Review-Instruct, a novel framework that synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman. The framework iteratively refines instructions by incorporating Reviewer feedback, enhancing dialogue diversity and difficulty. We construct a multi-turn dataset using the Alpaca dataset and fine-tune the LLaMA2-13B model. Evaluations on MT-Bench, MMLU-Pro, and Auto-Arena demonstrate significant improvements, achieving absolute gains of 2.9\% on MMLU-Pro and 2\% on MT-Bench compared to prior state-of-the-art models based on LLaMA2-13B. Ablation studies confirm the critical role of the Review stage and the use of multiple Reviewers in boosting instruction diversity and difficulty. Our work highlights the potential of review-driven, multi-agent frameworks for generating high-quality conversational data at scale.

Related papers

• VisualPRM: An Effective Process Reward Model for Multimodal Reasoning [76.35753243272521]
  We introduce VisualPRM, which improves the reasoning abilities of existing Multimodal Large Language Models (MLLMs)<n>Our model achieves a 5.9-point improvement across seven multimodal reasoning benchmarks.<n>For the evaluation of multimodal PRMs, we propose VisualProcessBench, a benchmark with human-annotated step-wise correctness labels.
  arXiv  Detail & Related papers  (2025-03-13T12:03:37Z)
• Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts [56.7225771305861]
  This paper introduces Multi-Modal Retrieval-Augmented Generation (M$2$RAG), a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models.<n>The benchmark comprises four tasks: image captioning, multi-modal question answering, multi-modal fact verification, and image reranking.<n>To enhance the context utilization capabilities of MLLMs, we also introduce Multi-Modal Retrieval-Augmented Instruction Tuning (MM-RAIT)
  arXiv  Detail & Related papers  (2025-02-24T16:25:25Z)
• Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions [62.0123588983514]
  Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields. We reformulate the peer-review process as a multi-turn, long-context dialogue, incorporating distinct roles for authors, reviewers, and decision makers. We construct a comprehensive dataset containing over 26,841 papers with 92,017 reviews collected from multiple sources.
  arXiv  Detail & Related papers  (2024-06-09T08:24:17Z)
• MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues [58.33076950775072]
  MT-Bench-101 is designed to evaluate the fine-grained abilities of Large Language Models (LLMs) in multi-turn dialogues. We construct a three-tier hierarchical ability taxonomy comprising 4208 turns across 1388 multi-turn dialogues in 13 distinct tasks. We then evaluate 21 popular LLMs based on MT-Bench-101, conducting comprehensive analyses from both ability and task perspectives.
  arXiv  Detail & Related papers  (2024-02-22T18:21:59Z)
• Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark [38.613625892808706]
  This paper introduces a new dataset SURE (Multimodal Recommendation Dialog with SUbjective PREference) The data is built in two phases with human annotations to ensure quality and diversity. SURE is well-annotated with subjective preferences and recommendation acts proposed by sales experts.
  arXiv  Detail & Related papers  (2023-05-26T08:43:46Z)
• Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions [1.6752182911522517]
  Self-Agreement is a novel framework for fine-tuning large language models to autonomously find agreement. Our approach employs the generative pre-trained transformer-3 to generate multiple opinions for each question in a question dataset. A bidirectional encoder representations from transformers (BERT)-based model selects the one with the highest agreement score. Remarkably, a pre-trained LLM fine-tuned by our Self-Agreement framework achieves comparable performance to GPT-3 with only 1/25 of its parameters.
  arXiv  Detail & Related papers  (2023-05-19T06:27:16Z)
• Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension [7.353227696624305]
  We tackle Multi-party Dialogue Reading (abbr., MDRC) MDRC stands for an extractive reading comprehension task grounded on a batch of dialogues among multiple interlocutors. We propose a coreference-aware attention modeling method to strengthen the reasoning ability.
  arXiv  Detail & Related papers  (2023-05-15T05:01:29Z)
• Large Language Models are Diverse Role-Players for Summarization Evaluation [82.31575622685902]
  A document summary's quality can be assessed by human annotators on various criteria, both objective ones like grammar and correctness, and subjective ones like informativeness, succinctness, and appeal. Most of the automatic evaluation methods like BLUE/ROUGE may be not able to adequately capture the above dimensions. We propose a new evaluation framework based on LLMs, which provides a comprehensive evaluation framework by comparing generated text and reference text from both objective and subjective aspects.
  arXiv  Detail & Related papers  (2023-03-27T10:40:59Z)
• Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue [50.279206765971125]
  We explore three methods to tackle the problem of interpreting multimodal inputs from conversational and situational contexts. Our best method, scene-dialogue alignment, improves the performance by 20% F1-score compared to the SIMMC 2.1 baselines.
  arXiv  Detail & Related papers  (2023-02-28T15:45:20Z)
• Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue [92.01165203498299]
  Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange. This paper argues that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research.
  arXiv  Detail & Related papers  (2022-10-10T05:51:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.