paper-with-me

Papers

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration

2025-03-19 · David Wan, Justin Chih-Yao Chen, Elias Stengel-Eskin, Mohit Bansal

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation, specifically to improving faithfulness through refinement, i.e., revising model-generated outputs to remove factual inconsistencies. We investigate how iterative collaboration among multiple instances and types of large language models (LLMs) enhances subtasks in the refinement process, such as error detection, critiquing unfaithful sentences, and making corrections based on critiques. We design intrinsic evaluations for each subtask, with our findings indicating that both multi-agent (multiple instances) and multi-model (diverse LLM types) approaches benefit error detection and critiquing. Additionally, reframing critiquing and refinement as reranking rather than generation tasks improves multi-agent performance. We consolidate these insights into a final "recipe" called Multi-Agent Multi-Model Refinement (MAMM-Refine), where multi-agent and multi-model collaboration significantly boosts performance on three summarization datasets as well as on long-form question answering, demonstrating the effectiveness and generalizability of our recipe.

📄 PDF Abstract BibTeX arXiv:2503.15272

Code (0)

등록된 구현이 없습니다.

Tasks

Long Form Question AnsweringQuestion AnsweringReranking

Similar Papers 제목 키워드 기반

CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes

2026-06-30 · Yuchen Huang, Xiang Li, Zhenqing Ling, Sijia Li 외 arxiv

Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While existing benchmarks either isolate text edi…

LLaVA-Chef: A Multi-modal Generative Model for Food Recipes

2024-08-29 · Fnu Mohbat, Mohammed J. Zaki

In the rapidly evolving landscape of online recipe sharing within a globalized context, there has been a notable surge in research towards comprehending and generating food recipes. Recent advancements in large language …

Recipe Generation

MammothModa: Multi-Modal Large Language Model

2024-06-26 · Qi She, Junwen Pan, Xin Wan, Rui Zhang 외

In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline. We focus on three key design insights: …

Language ModelingLanguage ModellingLarge Language Modelmodel+1

Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography

2025-07-23 · Farnoush Bayatmakou, Reza Taleei, Nicole Simone, Arash Mohammadi arxiv

Breast cancer (BC) remains one of the leading causes of cancer-related mortality among women, despite recent advances in Computer-Aided Diagnosis (CAD) systems. Accurate and efficient interpretation of multi-view mammogr…

Computational EfficiencyRepresentation Learning

Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate

2024-02-12 · Kyungha Kim, Sangyun Lee, Kung-Hsiang Huang, Hou Pong Chan 외

Fact-checking research has extensively explored verification but less so the generation of natural-language explanations, crucial for user trust. While Large Language Models (LLMs) excel in text generation, their capabil…

Fact CheckingText Generation