paper-with-me

Papers

PrefScore: Pairwise Preference Learning for Reference-free Summarization Quality Assessment

2022-10-01 · COLING 2022 10 · Ge Luo, Hebi Li, Youbiao He, Forrest Sheng Bao

Evaluating machine-generated summaries without a human-written reference summary has been a need for a long time. Inspired by preference labeling in existing work of summarization evaluation, we propose to judge summary quality by learning the preference rank of summaries using the Bradley-Terry power ranking model from inferior summaries generated by corrupting base summaries. Extensive experiments on several datasets show that our weakly supervised scheme can produce scores highly correlated with human ratings.

📄 PDF Abstract BibTeX

Code (1)

nkwbtb/prefscore 공식 구현 pytorch

Similar Papers 제목 키워드 기반

PrefScore: Pairwise Preference Learning for Reference-free Single-document Summarization Quality Assessment

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Evaluating machine-generated summaries without a human-written reference summary has been a need for a long time. Inspired by preference labeling in existing works of summarization evaluation, we propose to judge summary…

Document Summarization

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

2026-05-12 · Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van, Duy Minh Ho Nguyen 외 arxiv

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token dec…

Instruction Following

Multiple Pairwise Ranking Networks for Personalized Video Summarization

2021-01-01 · ICCV 2021 10 · Yassir Saquil, Da Chen, Yuan He, Chuan Li 외

In this paper, we investigate video summarization in the supervised setting. Since video summarization is subjective to the preference of the end-user, the design of a unique model is limited. In this work, we propos…

Video Summarization

Estimating Summary Quality with Pairwise Preferences

2018-06-01 · NAACL 2018 6 · Markus Zopf

Automatic evaluation systems in the field of automatic summarization have been relying on the availability of gold standard summaries for over ten years. Gold standard summaries are expensive to obtain and often require …

Text Summarization

Reward-free Alignment for Conflicting Objectives

2026-02-02 · Peter Chen, Xiaopeng Li, Xi Chen, Tianyi Lin arxiv

Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of…