Cover Image

Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mei, Xiaoyong, Zuo, Tingting, Chen, Da, Hu, Guangyu, Wen, Xiangyu, Duan, Chao, Zhang, Mingyan, Zheng, Fudan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
by: Xu, Zhichao, et al.
Published: (2025)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
by: Hanna, Michael, et al.
Published: (2024)

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
by: Zhou, Zhanhui, et al.
Published: (2023)

Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization
by: Jin, Keyan, et al.
Published: (2025)

Science and Faith in Dialogue
by: Eberlin, Marcos, et al.
Published: (2023)

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
by: Lu, Yen-Ju, et al.
Published: (2025)

WavReward: Spoken Dialogue Models With Generalist Reward Evaluators
by: Ji, Shengpeng, et al.
Published: (2025)

STORYSUMM: Evaluating Faithfulness in Story Summarization
by: Subbiah, Melanie, et al.
Published: (2024)

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
by: Chen, Fan, et al.
Published: (2022)

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
by: Zhao, Xiangyu, et al.
Published: (2026)

PILAF: Optimal Human Preference Sampling for Reward Modeling
by: Feng, Yunzhen, et al.
Published: (2025)

AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts
by: Wen, Yingpeng, et al.
Published: (2023)

Faithful Model Evaluation for Model-Based Metrics
by: Goyal, Palash, et al.
Published: (2023)

Learning from Self Critique and Refinement for Faithful LLM Summarization
by: Hu, Ting-Yao, et al.
Published: (2025)

Beyond Single-Reward: Multi-Pair, Multi-Perspective Preference Optimization for Machine Translation
by: Wang, Hao, et al.
Published: (2025)

Preference as Reward, Maximum Preference Optimization with Importance Sampling
by: Jiang, Zaifan, et al.
Published: (2023)

AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
by: Jia, Mengzhao, et al.
Published: (2025)

SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization
by: Cho, Sangwoo, et al.
Published: (2024)

Faithful Chart Summarization with ChaTS-Pi
by: Krichene, Syrine, et al.
Published: (2024)

On Positional Bias of Faithfulness for Long-form Summarization
by: Wan, David, et al.
Published: (2024)

Benchmarking LLMs on the Semantic Overlap Summarization Task
by: Salvador, John, et al.
Published: (2024)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
by: Nie, Shuo, et al.
Published: (2026)

From Faithfulness to Correctness: Generative Reward Models that Think Critically
by: Ma, Qiyao, et al.
Published: (2025)

Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences
by: Ghoshal, Asish, et al.
Published: (2022)

LEAF: Latent Diffusion with Efficient Encoder Distillation for Aligned Features in Medical Image Segmentation
by: Huang, Qilin, et al.
Published: (2025)

Beyond the Binary: Capturing Diverse Preferences With Reward Regularization
by: Padmakumar, Vishakh, et al.
Published: (2024)

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
by: Gong, Shizhan, et al.
Published: (2026)

Towards a Common Transnational Education Framework : Peculiarities in China Matter / Mingyan Hu, Linda Dianne Willis
by: Hu, Mingyan

Instructive Dialogue Summarization with Query Aggregations
by: Wang, Bin, et al.
Published: (2023)

Interplay between Quantum Metric and Hybridized Collective Modes in Flat-Band Superfluids
by: Liu, Yi, et al.
Published: (2026)

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
by: Cao, Zouying, et al.
Published: (2025)

Towards Comprehensive Preference Data Collection for Reward Modeling
by: Hu, Yulan, et al.
Published: (2024)

Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization
by: Mondshine, Itai, et al.
Published: (2025)

PerPO: Perceptual Preference Optimization via Discriminative Rewarding
by: Zhu, Zining, et al.
Published: (2025)

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
by: Xia, Yinan, et al.
Published: (2025)

Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
by: Wan, Yanming, et al.
Published: (2025)

On Extending Direct Preference Optimization to Accommodate Ties
by: Chen, Jinghong, et al.
Published: (2024)

SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
by: Lu, Jingyu, et al.
Published: (2026)

Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
by: Zheng, Xuejing, et al.
Published: (2024)

$\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning
by: Razumovskaia, Evgeniia, et al.
Published: (2023)