On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?

North American Chapter of the Association for Computational Linguistics (NAACL), 2022

17 April 2022

Nouha Dziri

Sivan Milton

Mo Yu

Osmar Zaiane

Siva Reddy

HILM

ArXiv (abs)PDF HTML

Papers citing "On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?"

27 / 127 papers shown

Title
SheetCopilot: Bringing Software Productivity to the Next Level through Large Language ModelsNeural Information Processing Systems (NeurIPS), 2023 Hongxin Li Jingran Su Yuntao Chen Qing Li Zhaoxiang Zhang LMTD 272 48 0 30 May 2023
The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Sabrina Chiesurin Dimitris Dimakopoulos Marco Antonio Sobrevilla Cabezudo Arash Eshghi Ioannis V. Papaioannou Verena Rieser Ioannis Konstas HILM 167 33 0 25 May 2023
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuningConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Ximing Lu Faeze Brahman Peter West Jaehun Jang Khyathi Chandu ... Bill Yuchen Lin Skyler Hallinan Xiang Ren Sean Welleck Yejin Choi 318 33 0 24 May 2023
Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language ModelsInternational Conference on Learning Representations (ICLR), 2023 Ashutosh Baheti Ximing Lu Faeze Brahman Ronan Le Bras Maarten Sap Mark O. Riedl 326 13 0 24 May 2023
The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Shuo Zhang Liangming Pan Junzhou Zhao Wenjie Wang HILM 220 1 0 23 May 2023
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language ModelsInternational Conference on Language Resources and Evaluation (LREC), 2023 Oana Ignat Zhijing Jin Artem Abzaliev Laura Biester Santiago Castro ... Verónica Pérez-Rosas Siqi Shen Zekun Wang Winston Wu Amélie Reymond LRM 316 8 0 21 May 2023
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of PerformanceAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Arjun Subramonian Xingdi Yuan Hal Daumé Su Lin Blodgett 200 22 0 15 May 2023
Evaluating Open-Domain Question Answering in the Era of Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Ehsan Kamalloo Nouha Dziri C. Clarke Davood Rafiei ELM 446 145 0 11 May 2023
SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model Nan Li Bo Kang T. D. Bie 109 21 0 17 Apr 2023
Scientists' Perspectives on the Potential for Generative AI in their Fields Meredith Ringel Morris AI4CE 145 47 0 04 Apr 2023
Elastic Weight Removal for Faithful and Abstractive Dialogue GenerationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 Nico Daheim Nouha Dziri Mrinmaya Sachan Iryna Gurevych Edoardo Ponti MoMe 249 32 0 30 Mar 2023
DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving AgentsClinical Natural Language Processing Workshop (ClinicalNLP), 2023 Varun Nair Elliot Schumacher Geoffrey Tso Anitha Kannan VLM 207 68 0 30 Mar 2023
Koala: An Index for Quantifying Overlaps with Pre-training CorporaConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Thuy-Trang Vu Xuanli He Gholamreza Haffari Ehsan Shareghi CLL 155 23 0 26 Mar 2023
ChatGPT is on the Horizon: Could a Large Language Model be Suitable for Intelligent Traffic Safety Research and Applications? Ou Zheng Mohamed Abdel-Aty Dongdong Wang Zijin Wang Shengxuan Ding LM&MA 221 19 0 06 Mar 2023
KILM: Knowledge Injection into Encoder-Decoder Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Yan Xu Mahdi Namazifar Devamanyu Hazarika Aishwarya Padmakumar Yang Liu Dilek Z. Hakkani-Tür KELM 158 33 0 17 Feb 2023
Learning with Rejection for Abstractive Text SummarizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Mengyao Cao Yue Dong Jingyi He Jackie C.K. Cheung 180 9 0 16 Feb 2023
Diving Deep into Modes of Fact Hallucinations in Dialogue SystemsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Souvik Das Sougata Saha Rohini Srihari HILM 198 40 0 11 Jan 2023
Improved Beam Search for Hallucination Mitigation in Abstractive Summarization A. Sridhar Erik M. Visser HILM 267 16 0 06 Dec 2022
RHO ( $ρ$ ): Reducing Hallucination in Open-domain Dialogues with Knowledge GroundingAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Ziwei Ji Zihan Liu Nayeon Lee Tiezheng Yu Bryan Wilie Mini Zeng Pascale Fung HILM 238 69 0 03 Dec 2022
Deanthropomorphising NLP: Can a Language Model Be Conscious?PLoS ONE (PLoS ONE), 2022 Matthew Shardlow Piotr Przybyła 226 10 0 21 Nov 2022
Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue SystemsInternational Conference on Language Resources and Evaluation (LREC), 2022 Songbo Hu Ivan Vulić Fangyu Liu Anna Korhonen 268 0 0 07 Nov 2022
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel ModelConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Nico Daheim David Thulke Christian Dugast Hermann Ney HILM 239 5 0 31 Oct 2022
RARR: Researching and Revising What Language Models Say, Using Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Luyu Gao Zhuyun Dai Panupong Pasupat Anthony Chen Arun Tejasvi Chaganty ... Vincent Zhao Ni Lao Hongrae Lee Da-Cheng Juan Kelvin Guu HILM KELM 667 282 0 17 Oct 2022
Improving alignment of dialogue agents via targeted human judgements Amelia Glaese Nat McAleese Maja Trkebacz John Aslanides Vlad Firoiu ... John F. J. Mellor Demis Hassabis Koray Kavukcuoglu Lisa Anne Hendricks G. Irving ALM AAML 517 628 0 28 Sep 2022
Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic ModelingKnowledge-Based Systems (KBS), 2022 Yizhe Yang Heyan Huang Yang Gao Jiawei Li 253 5 0 27 Apr 2022
FaithDial: A Faithful Benchmark for Information-Seeking DialogueTransactions of the Association for Computational Linguistics (TACL), 2022 Nouha Dziri Ehsan Kamalloo Sivan Milton Osmar Zaiane Mo Yu Edoardo Ponti Siva Reddy HILM 302 116 0 22 Apr 2022
Evaluating Attribution in Dialogue Systems: The BEGIN BenchmarkTransactions of the Association for Computational Linguistics (TACL), 2021 Nouha Dziri Hannah Rashkin Tal Linzen David Reitter ALM 461 93 0 30 Apr 2021