相关论文: Improving Summarization with Human Edits

While large language models (LLMs) can already achieve strong performance on standard generic summarization benchmarks, their performance on more complex summarization task settings is less studied. Therefore, we benchmark LLMs on…

In recent times, extracting valuable information from large text is making significant progress. Especially in the current era of social media, people expect quick bites of information. Automatic text summarization seeks to tackle this by…

A major challenge for scaling machine learning is training models to perform tasks that are very difficult or time-consuming for humans to evaluate. We present progress on this problem on the task of abstractive summarization of entire…

Span annotation - annotating specific text features at the span level - can be used to evaluate texts where single-score metrics fail to provide actionable feedback. Until recently, span annotation was done by human annotators or fine-tuned…

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model…

We examine evaluation of faithfulness to input data in the context of hotel highlights: brief LLM-generated summaries that capture unique features of accommodations. Through human evaluation campaigns involving categorical error assessment…

We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text. We argue that text offers greater expressiveness, enabling users to provide richer feedback than simple…

LLM-powered personalization agent systems employ Large Language Models (LLMs) to predict users' behavior from their past activities. However, their effectiveness often hinges on the ability to effectively leverage extensive, long user…

Human evaluation is increasingly critical for assessing large language models, capturing linguistic nuances, and reflecting user preferences more accurately than traditional automated metrics. However, the resource-intensive nature of this…

While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when evaluating long-form summaries. Through a…

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…

We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional…

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…

In an ever-expanding world of domain-specific knowledge, the increasing complexity of consuming, and storing information necessitates the generation of summaries from large information repositories. However, every persona of a domain has…

Conversational human-likeness plays a central role in human-AI interaction, yet it has remained difficult to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised…

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…

Text summarization has been a crucial problem in natural language processing (NLP) for several decades. It aims to condense lengthy documents into shorter versions while retaining the most critical information. Various methods have been…

We study how to fine-tune LLMs using user-edit deployment data consisting of a set of context, an agent's response, and user edits. This deployment data is naturally generated by users in applications such as LLMs-based writing assistants…

In this work, we explore the application of Large Language Models to zero-shot Lay Summarisation. We propose a novel two-stage framework for Lay Summarisation based on real-life processes, and find that summaries generated with this method…

LLMs and RAG systems are now capable of handling millions of input tokens or more. However, evaluating the output quality of such systems on long-context tasks remains challenging, as tasks like Needle-in-a-Haystack lack complexity. In this…