相关论文: ISQA: Informative Factuality Feedback for Scientif…

We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answers, and provide…

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…

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…

Conversational search aims to retrieve passages containing essential information to answer queries in a multi-turn conversation. In conversational search, reformulating context-dependent conversational queries into stand-alone forms is…

Neural abstractive summarization models are prone to generate content inconsistent with the source document, i.e. unfaithful. Existing automatic metrics do not capture such mistakes effectively. We tackle the problem of evaluating…

Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further \emph{post-}deployment based on user…

With the explosive growth of scientific publications, making the synthesis of scientific knowledge and fact checking becomes an increasingly complex task. In this paper, we propose a multi-task approach for verifying the scientific…

Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates recent developments…

Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity…

Long-form question answering (LFQA) poses a challenge as it involves generating detailed answers in the form of paragraphs, which go beyond simple yes/no responses or short factual answers. While existing QA models excel in questions with…

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:…

Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of…

A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce…

Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation…

Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and produce aggregate scores without explaining deficiencies or guiding improvement,…

Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging…

Semantic Question Answering (SQA) systems automatically interpret user questions expressed in a natural language in terms of semantic queries. This process involves uncertainty, such that the resulting queries do not always accurately match…

State-of-the-art summarization systems can generate highly fluent summaries. These summaries, however, may contain factual inconsistencies and/or information not present in the source. Hence, an important component of assessing the quality…

Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. This work proposes InfoLossQA, a framework to characterize and recover simplification-induced…

An abundance of datasets and availability of reliable evaluation metrics have resulted in strong progress in factoid question answering (QA). This progress, however, does not easily transfer to the task of long-form QA, where the goal is to…