相关论文: Learning to summarize from human feedback

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches often rely on monolithic…

Wide usage of ChatGPT has highlighted the potential of reinforcement learning from human feedback. However, its training pipeline relies on manual ranking, a resource-intensive process. To reduce labor costs, we propose a self-supervised…

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…

Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard datasets. While these PLMs excel in automatic evaluations, they frequently underperform in human evaluations, indicating a deviation between…

Long document summarization is an important and hard task in the field of natural language processing. A good performance of the long document summarization reveals the model has a decent understanding of the human language. Currently, most…

Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article. In this paper, we show that recent neural systems excessively exploit this trend, which although…

Learning from rationales seeks to augment model prediction accuracy using human-annotated rationales (i.e. subsets of input tokens) that justify their chosen labels, often in the form of intermediate or multitask supervision. While…

Automatic summarization of radiology reports is an essential application to reduce the burden on physicians. Previous studies have widely used the "pre-training, fine-tuning" strategy to adapt large language models (LLMs) for summarization.…

Pretrained language models often generate outputs that are not in line with human preferences, such as harmful text or factually incorrect summaries. Recent work approaches the above issues by learning from a simple form of human feedback:…

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize…

Opinion summarization is the task of automatically generating summaries for a set of reviews about a specific target (e.g., a movie or a product). Since the number of reviews for each target can be prohibitively large, neural network-based…

Exploring the tremendous amount of data efficiently to make a decision, similar to answering a complicated question, is challenging with many real-world application scenarios. In this context, automatic summarization has substantial…

Despite the recent advances in abstractive text summarization, current summarization models still suffer from generating factually inconsistent summaries, reducing their utility for real-world application. We argue that the main reason for…

In many scenarios, humans prefer a text-based representation of quantitative data over numerical, tabular, or graphical representations. The attractiveness of textual summaries for complex data has inspired research on data-to-text systems.…

Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on…

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

End-to-end speech summarization has been shown to improve performance over cascade baselines. However, such models are difficult to train on very large inputs (dozens of minutes or hours) owing to compute restrictions and are hence trained…

How reliably an automatic summarization evaluation metric replicates human judgments of summary quality is quantified by system-level correlations. We identify two ways in which the definition of the system-level correlation is inconsistent…