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

arXiv: https://arxiv.org/abs/2604.17188 · HTML: https://mlsanity.com/paper/2604.17188/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Builds on (most cited first, 30 of 35)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Direct Preference Optimization with an Offset](https://mlsanity.com/paper/2402.10571/) (2024)
- [Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method](https://mlsanity.com/paper/2305.13412/) (2023)
- [Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization](https://mlsanity.com/paper/2010.01672/) (2020)
- [RewardDance: Reward Scaling in Visual Generation](https://mlsanity.com/paper/2509.08826/) (2025)
- [Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents](https://mlsanity.com/paper/2110.10150/) (2021)
- [RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding](https://mlsanity.com/paper/2212.01588/) (2022)
- [TWEETSUMM -- A Dialog Summarization Dataset for Customer Service](https://mlsanity.com/paper/2111.11894/) (2021)
- [Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization](https://mlsanity.com/paper/2012.03502/) (2020)
- [RewardAnything: Generalizable Principle-Following Reward Models](https://mlsanity.com/paper/2506.03637/) (2025)
- [CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization](https://mlsanity.com/paper/2108.13139/) (2021)
- [Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends](https://mlsanity.com/paper/2406.03487/) (2024)
- [Learning to Summarize from LLM-generated Feedback](https://mlsanity.com/paper/2410.13116/) (2024)
- [TODSum: Task-Oriented Dialogue Summarization with State Tracking](https://mlsanity.com/paper/2110.12680/) (2021)
- [Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts](https://mlsanity.com/paper/2403.07556/) (2024)
- [Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization](https://mlsanity.com/paper/2404.00530/) (2024)
- [FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document](https://mlsanity.com/paper/2404.11184/) (2024)
- [CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization](https://mlsanity.com/paper/2508.09074/) (2025)
- [Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization](https://mlsanity.com/paper/2502.06185/) (2025)
- [Improving Factual Consistency of News Summarization by Contrastive Preference Optimization](https://mlsanity.com/paper/2310.19347/) (2023)

## Abstract (arXiv)

Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual consistency. However, most existing methods optimize for automatic metrics such as ROUGE and BERTScore, which favor surface-level imitation of references rather than genuine gains in faithfulness or alignment with human preferences. We propose a novel framework that couples explicit cognitive-style reasoning with reward-based optimization for multi-role dialogue summarization. Our method first distills structured reasoning traces (e.g., step-by-step inferences and intermediate reflections) from a large teacher model and uses them as auxiliary supervision to initialize a reasoning-aware summarizer via staged supervised fine-tuning. It then applies GRPO with a dual-principle reward that blends metric-based signals with human-aligned criteria targeting key information coverage, implicit inference, factual faithfulness, and conciseness. Experiments on multilingual multi-role dialogue benchmarks show that our method matches strong baselines on ROUGE and BERTScore. Specifically, results on CSDS confirm the framework's stability in semantic consistency, while in-depth analysis on SAMSum demonstrates clear gains in factual faithfulness and model-based preference alignment. These findings underscore the value of reasoning-aware and preference-aware training for reliable dialogue summarization. Checkpoints and datasets are available at https://huggingface.co/collections/NebulaPixel/summorchestra-multirole-summary.