中文
相关论文

相关论文: Rome was built in 1776: A Case Study on Factual Co…

200 篇论文

Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have demonstrated impressive capabilities in generating coherent and fluent text,…

计算与语言 · 计算机科学 2026-01-15 Shuqi Liu , Han Wu , Guanzhi Deng , Jianshu Chen , Xiaoyang Wang , Linqi Song

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

计算与语言 · 计算机科学 2024-04-09 Pouria Rouzrokh , Shahriar Faghani , Cooper U. Gamble , Moein Shariatnia , Bradley J. Erickson

Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires the identification of the disentangled latent…

机器学习 · 计算机科学 2024-02-26 Hanqi Yan , Lingjing Kong , Lin Gui , Yuejie Chi , Eric Xing , Yulan He , Kun Zhang

We analyze the Knowledge Neurons framework for the attribution of factual and relational knowledge to particular neurons in the transformer network. We use a 12-layer multi-lingual BERT model for our experiments. Our study reveals various…

计算与语言 · 计算机科学 2022-05-05 Jeevesh Juneja , Ritu Agarwal

Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect…

计算与语言 · 计算机科学 2026-05-29 Shicheng Fan , Haochang Hao , Dehai Min , Weihao Liu , Philip S. Yu , Lu Cheng

Information-seeking dialogues span a wide range of questions, from simple factoid to complex queries that require exploring multiple facets and viewpoints. When performing exploratory searches in unfamiliar domains, users may lack…

信息检索 · 计算机科学 2024-10-30 Weronika Łajewska , Krisztian Balog , Damiano Spina , Johanne Trippas

Recent named entity recognition (NER) models often rely on human-annotated datasets, requiring the significant engagement of professional knowledge on the target domain and entities. This research introduces an ask-to-generate approach that…

计算与语言 · 计算机科学 2022-11-08 Hyunjae Kim , Jaehyo Yoo , Seunghyun Yoon , Jinhyuk Lee , Jaewoo Kang

We show that existing evaluations for assessing the factuality of news from conventional sources, such as claims on fact-checking websites, result in high accuracies over time for LLM-based detectors-even after their knowledge cutoffs. This…

计算与语言 · 计算机科学 2025-07-29 Sanxing Chen , Yukun Huang , Bhuwan Dhingra

Long-form factuality evaluation assesses the ability of models to generate accurate, comprehensive responses to short prompts. Existing benchmarks often lack human verification, leading to potential quality issues. To address this…

计算与语言 · 计算机科学 2025-08-04 Mingda Chen , Yang Li , Xilun Chen , Adina Williams , Gargi Ghosh , Scott Yih

Despite recent advances in understanding the capabilities and limits of generative artificial intelligence (GenAI) models, we are just beginning to understand their capacity to assess and reason about the veracity of content. We evaluate…

Natural language understanding tasks such as open-domain question answering often require retrieving and assimilating factual information from multiple sources. We propose to address this problem by integrating a semi-parametric…

计算与语言 · 计算机科学 2022-04-21 Michiel de Jong , Yury Zemlyanskiy , Nicholas FitzGerald , Fei Sha , William Cohen

Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure of long-form…

计算与语言 · 计算机科学 2022-03-22 Fangyuan Xu , Junyi Jessy Li , Eunsol Choi

Creating high-quality and realistic images is now possible thanks to the impressive advancements in image generation. A description in natural language of your desired output is all you need to obtain breathtaking results. However, as the…

计算机视觉与模式识别 · 计算机科学 2024-03-15 Giuseppe Cartella , Vittorio Cuculo , Marcella Cornia , Rita Cucchiara

Neural network models are capable of generating extremely natural sounding conversational interactions. Nevertheless, these models have yet to demonstrate that they can incorporate content in the form of factual information or…

计算与语言 · 计算机科学 2018-11-19 Marjan Ghazvininejad , Chris Brockett , Ming-Wei Chang , Bill Dolan , Jianfeng Gao , Wen-tau Yih , Michel Galley

Knowledge-grounded dialogue is a task of generating a fluent and informative response based on both conversation context and a collection of external knowledge, in which knowledge selection plays an important role and attracts more and more…

计算与语言 · 计算机科学 2021-09-01 Shilei Liu , Xiaofeng Zhao , Bochao Li , Feiliang Ren

This study aims to generate responses based on real-world facts by conditioning context and external facts extracted from information websites. Our system is an ensemble system that combines three modules: generated-based module,…

计算与语言 · 计算机科学 2019-02-06 Ryota Tanaka , Akihide Ozeki , Shugo Kato , Akinobu Lee

We study question answering over a dynamic textual environment. Although neural network models achieve impressive accuracy via learning from input-output examples, they rarely leverage various types of knowledge and are generally not…

计算与语言 · 计算机科学 2020-04-28 Wanjun Zhong , Duyu Tang , Nan Duan , Ming Zhou , Jiahai Wang , Jian Yin

Counterfactuals have become a popular technique nowadays for interacting with black-box machine learning models and understanding how to change a particular instance to obtain a desired outcome from the model. However, most existing…

机器学习 · 计算机科学 2021-09-29 Philip Naumann , Eirini Ntoutsi

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Le Zhuo , Songhao Han , Yuandong Pu , Boxiang Qiu , Sayak Paul , Yue Liao , Yihao Liu , Jie Shao , Xi Chen , Si Liu , Hongsheng Li

Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries. In this paper, we show that factual inconsistency can be caused by…