English
Related papers

Related papers: Learning to summarize from human feedback

200 papers

Pre-trained and fine-tuned news summarizers are expected to generalize to news articles unseen in the fine-tuning (training) phase. However, these articles often contain specifics, such as new events and people, a summarizer could not learn…

Computation and Language · Computer Science 2022-04-19 Arthur Bražinskas , Mengwen Liu , Ramesh Nallapati , Sujith Ravi , Markus Dreyer

Automatically generating short summaries from users' online mental health posts could save counselors' reading time and reduce their fatigue so that they can provide timely responses to those seeking help for improving their mental state.…

Computation and Language · Computer Science 2023-02-03 Sajad Sotudeh , Nazli Goharian , Hanieh Deilamsalehy , Franck Dernoncourt

Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation…

Computation and Language · Computer Science 2024-03-19 Zhiwei He , Xing Wang , Wenxiang Jiao , Zhuosheng Zhang , Rui Wang , Shuming Shi , Zhaopeng Tu

In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, although Large Language Models (LLMs) can generate fluent…

Computation and Language · Computer Science 2024-10-03 Jaepill Choi , Kyubyung Chae , Jiwoo Song , Yohan Jo , Taesup Kim

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and…

Computation and Language · Computer Science 2025-12-25 Jiayi Zhou , Jiaming Ji , Juntao Dai , Dong Li , Yaodong Yang

We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries…

Computation and Language · Computer Science 2022-06-15 William Saunders , Catherine Yeh , Jeff Wu , Steven Bills , Long Ouyang , Jonathan Ward , Jan Leike

Evaluating multi-document summarization (MDS) quality is difficult. This is especially true in the case of MDS for biomedical literature reviews, where models must synthesize contradicting evidence reported across different documents. Prior…

Computation and Language · Computer Science 2023-05-24 Lucy Lu Wang , Yulia Otmakhova , Jay DeYoung , Thinh Hung Truong , Bailey E. Kuehl , Erin Bransom , Byron C. Wallace

Existing multi-document summarization approaches produce a uniform summary for all users without considering individuals' interests, which is highly impractical. Making a user-specific summary is a challenging task as it requires: i)…

Information Retrieval · Computer Science 2024-08-15 Samira Ghodratnama , Mehrdad Zakershahrak

Document summarisation can be formulated as a sequential decision-making problem, which can be solved by Reinforcement Learning (RL) algorithms. The predominant RL paradigm for summarisation learns a cross-input policy, which requires…

Computation and Language · Computer Science 2019-07-31 Yang Gao , Christian M. Meyer , Mohsen Mesgar , Iryna Gurevych

Summarizing texts is not a straightforward task. Before even considering text summarization, one should determine what kind of summary is expected. How much should the information be compressed? Is it relevant to reformulate or should the…

Computation and Language · Computer Science 2020-07-16 Paul Tardy , David Janiszek , Yannick Estève , Vincent Nguyen

Summary assessment involves evaluating how well a generated summary reflects the key ideas and meaning of the source text, requiring a deep understanding of the content. Large Language Models (LLMs) have been used to automate this process,…

Computation and Language · Computer Science 2025-12-23 Zahra Sadeghi , Evangelos Milios , Frank Rudzicz

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by…

Computation and Language · Computer Science 2024-10-28 Alizée Pace , Jonathan Mallinson , Eric Malmi , Sebastian Krause , Aliaksei Severyn

Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…

Computation and Language · Computer Science 2023-10-31 Zeqiu Wu , Yushi Hu , Weijia Shi , Nouha Dziri , Alane Suhr , Prithviraj Ammanabrolu , Noah A. Smith , Mari Ostendorf , Hannaneh Hajishirzi

Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However,…

Machine Learning · Computer Science 2020-10-13 Arthur Bražinskas , Mirella Lapata , Ivan Titov

Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when…

Computation and Language · Computer Science 2018-04-20 Yuxiang Wu , Baotian Hu

Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in…

Computation and Language · Computer Science 2018-05-11 Bingzhen Wei , Xuancheng Ren , Xu Sun , Yi Zhang , Xiaoyan Cai , Qi Su

Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization…

Computation and Language · Computer Science 2026-04-29 Huyen Nguyen , Haoxuan Zhang , Yang Zhang , Junhua Ding , Haihua Chen

Sequence-to-sequence neural networks have recently achieved great success in abstractive summarization, especially through fine-tuning large pre-trained language models on the downstream dataset. These models are typically decoded with beam…

Computation and Language · Computer Science 2023-05-29 Mathieu Ravaut , Shafiq Joty , Nancy F. Chen

Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose LLMRefine, an inference time…

Computation and Language · Computer Science 2024-10-28 Wenda Xu , Daniel Deutsch , Mara Finkelstein , Juraj Juraska , Biao Zhang , Zhongtao Liu , William Yang Wang , Lei Li , Markus Freitag