paper-with-me

홈 › Papers

Incentive-Aligned Multi-Source LLM Summaries

2025-09-29 · Yanchen Jiang, Zhe Feng, Aranyak Mehta arxiv

Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and are vulnerable to adversarial content. We introduce Truthful Text Summarization (TTS), an incentive-aligned framework that improves factual robustness without ground-truth labels. TTS (i) decomposes a draft synthesis into atomic claims, (ii) elicits each source's stance on every claim, (iii) scores sources with an adapted multi-task peer-prediction mechanism that rewards informative agreement, and (iv) filters unreliable sources before re-summarizing. We establish formal guarantees that align a source's incentives with informative honesty, making truthful reporting the utility-maximizing strategy. Experiments show that TTS improves factual accuracy and robustness while preserving fluency, aligning exposure with informative corroboration and disincentivizing manipulation.

📄 PDF Abstract BibTeX arXiv:2509.25184

Code (0)

등록된 구현이 없습니다.

Tasks

Text Summarization

Similar Papers 제목 키워드 기반

Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas

2026-01-29 · Manuela Chacon-Chamorro, Luis Felipe Giraldo, Nicanor Quijano arxiv

Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems highly vulnerable to collapse under disruptions. In …

Multi-agent Reinforcement Learning

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption

2025-10-21 · Yepeng Liu, Xuandong Zhao, Dawn Song, Gregory W. Wornell 외 arxiv

Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among LLM providers, platforms, and end users, …

Crowd-Sourced Iterative Annotation for Narrative Summarization Corpora

2017-04-01 · EACL 2017 4 · Jessica Ouyang, Serina Chang, Kathy Mckeown

We present an iterative annotation process for producing aligned, parallel corpora of abstractive and extractive summaries for narrative. Our approach uses a combination of trained annotators and crowd-sourcing, allowing…

Abstractive Text SummarizationSentence CompressionText GenerationText Summarization

Leaderboard Incentives: Model Rankings under Strategic Post-Training

2026-03-09 · Yatong Chen, Guanhua Zhang, Moritz Hardt arxiv

Influential benchmarks incentivize competing model developers to strategically allocate post-training resources toward improvements on the leaderboard, a phenomenon dubbed benchmaxxing or training on the test task. In th…

Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization

2023-05-26 · Pranav Ajit Nair, Sukomal Pal, Pradeepika Verma

Domain generalization is hitherto an underexplored area applied in abstractive summarization. Moreover, most existing works on domain generalization have sophisticated training algorithms. In this paper, we propose a lig…

Abstractive Text SummarizationDomain Generalization