中文
相关论文

相关论文: ED-FAITH: Evaluating Dialogue Summarization on Fai…

200 篇论文

The problems of unfaithful summaries have been widely discussed under the context of abstractive summarization. Though extractive summarization is less prone to the common unfaithfulness issues of abstractive summaries, does that mean…

计算与语言 · 计算机科学 2023-05-31 Shiyue Zhang , David Wan , Mohit Bansal

Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions.…

计算与语言 · 计算机科学 2026-05-26 Yoav Gur-Arieh , Ana Marasović , Mor Geva

In this work, we evaluate various existing dialogue relevance metrics, find strong dependency on the dataset, often with poor correlation with human scores of relevance, and propose modifications to reduce data requirements and domain…

计算与语言 · 计算机科学 2022-06-07 Ian Berlot-Attwell , Frank Rudzicz

Automated source code summarization is a popular software engineering research topic wherein machine translation models are employed to "translate" code snippets into relevant natural language descriptions. Most evaluations of such models…

软件工程 · 计算机科学 2021-06-17 Junayed Mahmud , Fahim Faisal , Raihan Islam Arnob , Antonios Anastasopoulos , Kevin Moran

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…

计算与语言 · 计算机科学 2026-05-27 Yuxuan Ye , Raul Santos-Rodriguez , Edwin Simpson

In contrast with goal-oriented dialogue, social dialogue has no clear measure of task success. Consequently, evaluation of these systems is notoriously hard. In this paper, we review current evaluation methods, focusing on automatic…

计算与语言 · 计算机科学 2017-09-14 Amanda Cercas Curry , Helen Hastie , Verena Rieser

In this paper, we describe a set of metrics for the evaluation of different dialogue management strategies in an implemented real-time spoken language system. The set of metrics we propose offers useful insights in evaluating how particular…

cmp-lg · 计算机科学 2008-02-03 Morena Danieli , Elisabetta Gerbino

Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where conventional metrics struggle with input length limitations and long-range dependencies. In this…

计算与语言 · 计算机科学 2026-04-30 Zain Muhammad Mujahid , Dustin Wright , Isabelle Augenstein

The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems' outputs. However, the ever-evolving…

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…

Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a…

计算与语言 · 计算机科学 2020-10-14 Prakhar Ganesh , Saket Dingliwal

Automatically evaluating the quality of responses in open-domain dialogue systems is a challenging but crucial task. Current evaluation metrics often fail to align with human judgments, especially when assessing responses that are…

计算与语言 · 计算机科学 2024-06-26 Tao Feng , Lizhen Qu , Xiaoxi Kang , Gholamreza Haffari

The quality of a summarization evaluation metric is quantified by calculating the correlation between its scores and human annotations across a large number of summaries. Currently, it is unclear how precise these correlation estimates are,…

计算与语言 · 计算机科学 2021-07-28 Daniel Deutsch , Rotem Dror , Dan Roth

We present a methodology for improving the accuracy of faithfulness evaluation in Large Language Models (LLMs). The proposed methodology is based on the combination of elementary faithfulness metrics into a combined (fused) metric, for the…

计算与语言 · 计算机科学 2025-12-08 Ben Malin , Tatiana Kalganova , Nikolaos Boulgouris

Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although reviews have been conducted on this topic, there is a lack of comprehensive work detailing the challenges of…

计算与语言 · 计算机科学 2025-04-25 Frederic Kirstein , Jan Philip Wahle , Bela Gipp , Terry Ruas

Cutting-edge abstractive summarisers generate fluent summaries, but the factuality of the generated text is not guaranteed. Early summary factuality evaluation metrics are usually based on n-gram overlap and embedding similarity, but are…

计算与语言 · 计算机科学 2024-09-24 Yuxuan Ye , Edwin Simpson , Raul Santos Rodriguez

LLMs (Large Language Models) usually interact with users in the form of dialogue and generate responses following their instructions, which naturally require dialogue comprehension abilities. However, dialogue comprehension is a general…

计算与语言 · 计算机科学 2024-04-02 Shuaijie She , Shujian Huang , Xingyun Wang , Yanke Zhou , Jiajun Chen

A model's capacity to generalize its knowledge to interpret unseen inputs with different characteristics is crucial to build robust and reliable machine learning systems. Language model evaluation tasks lack information metrics about model…

计算与语言 · 计算机科学 2024-09-10 Saksham Bassi , Duygu Ataman , Kyunghyun Cho

It is well known that the standard likelihood training and approximate decoding objectives in neural text generation models lead to less human-like responses for open-ended tasks such as language modeling and story generation. In this paper…

计算与语言 · 计算机科学 2020-05-05 Joshua Maynez , Shashi Narayan , Bernd Bohnet , Ryan McDonald

Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documents. In this paper, we analyze the tradeoff between…

计算与语言 · 计算机科学 2023-04-26 Markus Dreyer , Mengwen Liu , Feng Nan , Sandeep Atluri , Sujith Ravi