English
Related papers

Related papers: A Factuality and Diversity Reconciled Decoding Met…

200 papers

Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain.…

Computation and Language · Computer Science 2020-02-25 Xueliang Zhao , Wei Wu , Chongyang Tao , Can Xu , Dongyan Zhao , Rui Yan

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…

Computation and Language · Computer Science 2023-10-17 Yixin Liu , Budhaditya Deb , Milagro Teruel , Aaron Halfaker , Dragomir Radev , Ahmed H. Awadallah

Traditional automated metrics for evaluating conditional natural language generation use pairwise comparisons between a single generated text and the best-matching gold-standard ground truth text. When multiple ground truths are available,…

Computation and Language · Computer Science 2022-09-30 David M Chan , Yiming Ni , David A Ross , Sudheendra Vijayanarasimhan , Austin Myers , John Canny

Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text, raising concerns about their reliability. Previous methods use external knowledge as references for text generation to…

Computation and Language · Computer Science 2023-08-31 Hongjin Qian , Zhicheng Dou , Jiejun Tan , Haonan Chen , Haoqi Gu , Ruofei Lai , Xinyu Zhang , Zhao Cao , Ji-Rong Wen

Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability. Inspired by recent work on evaluating…

Computation and Language · Computer Science 2021-09-10 Or Honovich , Leshem Choshen , Roee Aharoni , Ella Neeman , Idan Szpektor , Omri Abend

Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that are less informative but highly factual, or more informative…

Computation and Language · Computer Science 2026-02-03 Ziwei Gong , Yanda Chen , Julia Hirschberg , Chen Zhao , He He , Zhou Yu , Kathleen Mckeown

Knowledge Graph Question Answering (KGQA) aims to improve factual accuracy by leveraging structured knowledge. However, real-world Knowledge Graphs (KGs) are often incomplete, leading to the problem of Incomplete KGQA (IKGQA). A common…

Artificial Intelligence · Computer Science 2025-12-08 Jilong Liu , Pengyang Shao , Wei Qin , Fei Liu , Yonghui Yang , Richang Hong

Large Language Models (LLMs) augmented with retrieval mechanisms have demonstrated significant potential in fact-checking tasks by integrating external knowledge. However, their reliability decreases when confronted with conflicting…

Computation and Language · Computer Science 2025-05-26 Ziyu Ge , Yuhao Wu , Daniel Wai Kit Chin , Roy Ka-Wei Lee , Rui Cao

Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience.…

Artificial Intelligence · Computer Science 2025-12-09 Tingyu Li , Zheng Sun , Jingxuan Wei , Siyuan Li , Conghui He , Lijun Wu , Cheng Tan

Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved…

Computation and Language · Computer Science 2023-05-24 Yilun Du , Shuang Li , Antonio Torralba , Joshua B. Tenenbaum , Igor Mordatch

A major concern in using deep learning based generative models for document-grounded dialogs is the potential generation of responses that are not \textit{faithful} to the underlying document. Existing automated metrics used for evaluating…

Computation and Language · Computer Science 2023-12-04 Yatin Nandwani , Vineet Kumar , Dinesh Raghu , Sachindra Joshi , Luis A. Lastras

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

Computation and Language · Computer Science 2026-01-15 Giorgio Franceschelli , Mirco Musolesi

The construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, collecting…

Computation and Language · Computer Science 2022-11-01 Jiao Ou , Jinchao Zhang , Yang Feng , Jie Zhou

Grounding dialogue response generation on external knowledge is proposed to produce informative and engaging responses. However, current knowledge-grounded dialogue (KGD) systems often fail to align the generated responses with…

Computation and Language · Computer Science 2023-09-20 Bryan Wilie , Yan Xu , Willy Chung , Samuel Cahyawijaya , Holy Lovenia , Pascale Fung

Natural Language Processing and Generation systems have recently shown the potential to complement and streamline the costly and time-consuming job of professional fact-checkers. In this work, we lift several constraints of current…

Computation and Language · Computer Science 2025-10-30 Daniel Russo , Stefano Menini , Jacopo Staiano , Marco Guerini

We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a dialogue system that is engaging as a conversational partner. We propose a generator-evaluator model that evaluates multiple responses…

Computation and Language · Computer Science 2022-06-13 Ryoma Sakaeda , Daisuke Kawahara

In open-ended natural-language generation, existing text decoding methods typically struggle to produce text which is both diverse and high-quality. Greedy and beam search are known to suffer from text degeneration and linguistic diversity…

Computation and Language · Computer Science 2022-11-15 Mirac Suzgun , Luke Melas-Kyriazi , Dan Jurafsky

Persona and Knowledge dual context open-domain chat is a novel dialogue generation task introduced recently. While Persona and Knowledge is each interesting context of open-domain dialogue, the combination of both has not been well studied.…

Computation and Language · Computer Science 2022-07-29 Min Sik Oh , Min Sang Kim

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and…

Computation and Language · Computer Science 2022-04-21 Md Rashad Al Hasan Rony , Ricardo Usbeck , Jens Lehmann

With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge. However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in…

Computation and Language · Computer Science 2024-06-17 Ryohei Kamei , Daiki Shiono , Reina Akama , Jun Suzuki