相关论文: Learning to summarize from human feedback

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Conventional dialogue summarization methods directly generate summaries and do not consider user's specific interests. This poses challenges in cases where the users are more focused on particular topics or aspects. With the advancement of…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of…

To predict what someone will say is to model how they think. We study this through next-turn dialogue prediction: given a conversation, predict the next utterance produced by a person. We compare learning approaches along two dimensions:…

This paper presents a novel approach for unsupervised video summarization using reinforcement learning (RL), addressing limitations like unstable adversarial training and reliance on heuristic-based reward functions. The method operates on…

We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively…

Human language production exhibits remarkable richness and variation, reflecting diverse communication styles and intents. However, this variation is often overlooked in summarization evaluation. While having multiple reference summaries is…

Recent Transformer-based summarization models have provided a promising approach to abstractive summarization. They go beyond sentence selection and extractive strategies to deal with more complicated tasks such as novel word generation and…

Neural abstractive summarization has been widely studied and achieved great success with large-scale corpora. However, the considerable cost of annotating data motivates the need for learning strategies under low-resource settings. In this…

Current abstractive summarization systems present important weaknesses which prevent their deployment in real-world applications, such as the omission of relevant information and the generation of factual inconsistencies (also known as…

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…

Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative…

Research on automated text summarization relies heavily on human and automatic evaluation. While recent work on human evaluation mainly adopted intrinsic evaluation methods, judging the generic quality of text summaries, e.g.…

Reference-based metrics such as ROUGE or BERTScore evaluate the content quality of a summary by comparing the summary to a reference. Ideally, this comparison should measure the summary's information quality by calculating how much…

3D content creation from text prompts has shown remarkable success recently. However, current text-to-3D methods often generate 3D results that do not align well with human preferences. In this paper, we present a comprehensive framework,…

Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and…

Opinion summarization has been traditionally approached with unsupervised, weakly-supervised and few-shot learning techniques. In this work, we collect a large dataset of summaries paired with user reviews for over 31,000 products, enabling…

The advancements in deep learning, particularly the introduction of transformers, have been pivotal in enhancing various natural language processing (NLP) tasks. These include text-to-text applications such as machine translation, text…