FaithDial: A Faithful Benchmark for Information-Seeking Dialogue
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination. To mitigate this behavior, we adopt a data-centric solution and create FaithDial, a new benchmark for hallucination-free dialogues, by editing hallucinated responses in the Wizard of Wikipedia (WoW) benchmark. We observe that FaithDial is more faithful than WoW while also maintaining engaging conversations. We show that FaithDial can serve as training signal for: i) a hallucination critic, which discriminates whether an utterance is faithful or not, and boosts the performance by 12.8 F1 score on the BEGIN benchmark compared to existing datasets for dialogue coherence; ii) high-quality dialogue generation. We benchmark a series of state-of-the-art models and propose an auxiliary contrastive objective that achieves the highest level of faithfulness and abstractiveness based on several automated metrics. Further, we find that the benefits of FaithDial generalize to zero-shot transfer on other datasets, such as CMU-Dog and TopicalChat. Finally, human evaluation reveals that responses generated by models trained on FaithDial are perceived as more interpretable, cooperative, and engaging.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“DoHA augments BART (Lewis et al., 2020) with a two-view attention mechanism that separately handles the knowledge document and the dialogue history during generation.”
BackgroundTransformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1×
“By mimicking the distributional properties of the data, models are bound to ‘‘parrot’’ the hallucinated signals at test time (Bender et al., 2021).”
BackgroundSurvey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1×
“Hallucination in knowledge-grounded neural language generation has recently received increasing attention from the NLP community (Ji et al., 2022).”
BackgroundSurvey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y., Chen, D., Dai, W., et al. (2022) · arXiv · doi:10.48550/arxiv.2202.03629 · Cited by 4,981
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342 · cited 7×
“Surprisingly, MNLI transfers well to F AITH C RITIC .”
BackgroundMethodInfluentialBERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
Cognitive load theory, educational research, and instructional design: some food for thought
de Jong, T. (2010) · Instructional Science · doi:10.1007/s11251-009-9110-0 · Cited by 1,180 · cited 1×
“Moreover, knowledge snippets in W O W tend to be shorter, which is preferable as longer knowledge is correlated with increased hallucination due to the constrained cognitive capacity for text navigation and comprehension in humans (De Jong, 2010; DeStefano and LeFevre, 2007).”
BackgroundDIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation
Zhang, Y., Sun, S., Galley, M., Chen, Y.-C., Brockett, C., Gao, X., Gao, J., Liu, J., & Dolan, B. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/2020.acl-demos.30 · Cited by 1,076
Recipes for Building an Open-Domain Chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Smith, E. M., Boureau, Y.-L., et al. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.24 · Cited by 784
Recipes for building an open-domain chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Shuster, K., Smith, E. M., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.13637 · Cited by 784 · cited 3×
“We benchmark a series of state-of-the-art dialogue models (Radford et al., 2019; Roller et al., 2021; Raffel et al., 2020; Rashkin et al., 2021b) on FAITHDIAL.”
BackgroundLaMDA: Language Models for Dialog Applications
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.08239 · Cited by 778
Retrieval Augmentation Reduces Hallucination in Conversation
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.320 · Cited by 575
Challenges in Data-to-Document Generation
Wiseman, S., Shieber, S., & Rush, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1239 · Cited by 524
Crowdsourcing research: Data collection with Amazon’s Mechanical Turk
Sheehan, K. B. (2018) · Communication Monographs · doi:10.1080/03637751.2017.1342043 · Cited by 408 · cited 1×
“Following the guidelines for ethical crowdsourcing outlined in Sheehan (2018), we hire Amazon Mechanical Turk (AMT) workers to edit utterances in W O W dialogues that were found to exhibit un-faithful responses.”
Method(2020) · doi:10.18653/v1/2020.acl-main.450 · Cited by 356
Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
Wang, A., Cho, K., & Lewis, M. (2020) · arXiv · doi:10.48550/arxiv.2004.04228 · Cited by 356 · cited 1×
“Then, it identifies possible spans in the knowledge source and the candidate response to justify the question–answer pairs (Durmus et al., 2020; Wang et al., 2020).”
BackgroundDurmus, E., He, H., & Diab, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.454 · Cited by 306
ToTTo: A Controlled Table-To-Text Generation Dataset
Parikh, A., Wang, X., Gehrmann, S., Faruqui, M., Dhingra, B., Yang, D., & Das, D. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.89 · Cited by 252
ToTTo: A Controlled Table-To-Text Generation Dataset
Parikh, A. P., Wang, X., Gehrmann, S., Faruqui, M., Dhingra, B., Yang, D., & Das, D. (2020) · arXiv · doi:10.48550/arxiv.2004.14373 · Cited by 252 · cited 1×
“Tasks include data-to-text generation (Wiseman et al., 2017; Parikh et al., 2020), machine translation (Raunak et al.”
MethodDialogue Natural Language Inference
Welleck, S., Weston, J., Szlam, A., & Cho, K. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1363 · Cited by 249 · cited 2×
“This characterization of the problem is reminiscent of previous work (Dziri et al., 2019; Welleck et al., 2019b; Nie et al., 2021) on detecting contradiction within a conversation.”
MethodResultTopical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
Gopalakrishnan, K., Hedayatnia, B., Chen, Q., Gottardi, A., Kwatra, S., Venkatesh, A., Gabriel, R., & Hakkani-Tür, D. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-3079 · Cited by 207
The Curious Case of Hallucinations in Neural Machine Translation
Raunak, V., Menezes, A., & Junczys-Dowmunt, M. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.92 · Cited by 142
The Curious Case of Hallucinations in Neural Machine Translation
Raunak, V., Menezes, A., & Junczys-Dowmunt, M. (2021) · arXiv · doi:10.48550/arxiv.2104.06683 · Cited by 142 · cited 2×
“, 2017) or finding possible causes for this degenerate behaviour, including outof-domain generalization and noisy training data points (Kang and Hashimoto, 2020; Raunak et al., 2021) and exposure bias caused by MLE training (Wang and Sennrich, 2020).”
BackgroundOn the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Dziri, N., Milton, S., Yu, M., Zaiane, O., & Reddy, S. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.387 · Cited by 121
Self-citationOn Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
Wang, C., & Sennrich, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.326 · Cited by 118
Honovich, O., Choshen, L., Aharoni, R., Neeman, E., Szpektor, I., & Abend, O. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.619 · Cited by 113
Annotating and Modeling Fine-grained Factuality in Summarization
Goyal, T., & Durrett, G. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.114 · Cited by 100
Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding
Dziri, N., Madotto, A., Zaïane, O., & Bose, A. J. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.168 · Cited by 81 · cited 2×
“, 2021b), by learning a token-level hallucination critic to flag problematic entities and replace them (Dziri et al., 2021), or by augmenting the dialogue system with a module retrieving relevant knowledge (Shuster et al.”
BackgroundSelf-citationIncreasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
Rashkin, H., Reitter, D., Tomar, G. S., & Das, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.58 · Cited by 74 · cited 14×
“We choose the best vanilla model T5 as the back-bone for CTRL, I NFO NCE and L OSS T RUNCA - TION .”
BackgroundInfluentialReducing conversational agents' overconfidence through linguistic calibration
Mielke, S. J., Szlam, A., Dinan, E., & Boureau, Y.-L. (2020) · arXiv · doi:10.48550/arxiv.2012.14983 · Cited by 72 · cited 1×
“Hallucinations in knowledge-grounded neural dialogue generation is instead a nascent research problem (Roller et al., 2021; Mielke et al., 2020; Shuster et al., 2021; Dziri et al., 2021a; Rashkin et al., 2021b).”
BackgroundReducing Conversational Agents’ Overconfidence Through Linguistic Calibration
Mielke, S. J., Szlam, A., Dinan, E., & Boureau, Y.-L. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00494 · Cited by 72 · cited 1×
“Hallucinations in knowledge-grounded neural dialogue generation is an emergent research problem (Roller et al., 2021; Mielke et al., 2022; Shuster et al., 2021; Dziri et al., 2021; Rashkin et al., 2021b).”
BackgroundDialFact: A Benchmark for Fact-Checking in Dialogue
Gupta, P., Wu, C.-S., Liu, W., & Xiong, C. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.263 · Cited by 48
Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark
Dziri, N., Rashkin, H., Linzen, T., & Reitter, D. (2021) · arXiv · doi:10.48550/arxiv.2105.00071 · Cited by 47 · cited 7×
“Recently introduced benchmarks can serve as testbeds for knowledge grounding in dialogue systems, such as BEGIN (Dziri et al., 2021b), DialFact (Gupta et al.”
BackgroundMethodInfluentialSelf-citationLadhak, F., Durmus, E., He, H., Cardie, C., & McKeown, K. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.100 · Cited by 46
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning
Tang, X., Nair, A., Wang, B., Wang, B., Desai, J., Wade, A., Li, H., Celikyilmaz, A., Mehdad, Y., & Radev, D. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.415 · Cited by 43
Measuring Attribution in Natural Language Generation Models
Rashkin, H., Nikolaev, V., Lamm, M., Aroyo, L., Collins, M., Das, D., Petrov, S., Tomar, G. S., Turc, I., & Reitter, D. (2021) · arXiv · doi:10.48550/arxiv.2112.12870 · Cited by 34
Santhanam, S., Hedayatnia, B., Gella, S., Padmakumar, A., Kim, S., Liu, Y., & Hakkani-Tur, D. (2021) · arXiv · doi:10.48550/arxiv.2110.05456 · Cited by 21 · cited 1×
“Recently introduced benchmarks can serve as testbeds for knowledge grounding in dialogue systems, such as BEGIN (Dziri et al., 2022b), DialFact (Gupta et al., 2022), Conv-FEVER (Santhanam et al., 2021) and At-tributable to Identified Sources (AIS) framework (Rashkin et al., 2021a).”
BackgroundOn the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Dziri, N., Milton, S., Yu, M., Zaiane, O., & Reddy, S. (2022) · arXiv · doi:10.48550/arxiv.2204.07931 · Cited by 13
Self-citationOn Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
Wang, C., & Sennrich, R. (2020) · arXiv · doi:10.48550/arxiv.2005.03642 · Cited by 12 · cited 1×
“, 2021) and exposure bias caused by MLE training (Wang and Sennrich, 2020).”
Background
Research works printed but not linked: 22
- Cao, 2021, CLIFF: Contrastive learning for improving faithfulness and factuality in abstractive summarization, 6633, 10.18653/v1/2021.emnlp-main.532 · DOI · Paper page
- DeStefano, 2007, Cognitive load in hypertext reading: A review, Computers in Human Behavior, 23, 1616, 10.1016/j.chb.2005.08.012 · DOI · Paper page
- Dinan, 2019, Wizard of Wikipedia: Knowledge- powered conversational agents
- Dziri, 2019, Evaluating coherence in dialogue systems using entailment, 3806, 10.18653/v1/N19-1381 · DOI · Paper page
- Grusky, 2018, Newsroom: A dataset of 1.3 million summaries with diverse extractive strategies, 708, 10.18653/v1/N18-1065 · DOI · Paper page
- Kang, 2020, Improved natural language generation via loss truncation, 718, 10.18653/v1/2020.acl-main.66 · DOI · Paper page
- Richard Landis, 1977, The measurement of observer agreement for categorical data, biometrics, 159, 10.2307/2529310 · DOI · Paper page
- Li, 2021, Addressing semantic drift in generative question answering with auxiliary extraction, 942, 10.18653/v1/2021.acl-short.118 · DOI
- Lin, 2004, ROUGE: A package for automatic evaluation of summaries, 74
- Liu, 2019, Roberta: A robustly optimized BERT pretraining approach, CoRR
- Lux, 2020, Truth or error? Towards systematic analysis of factual errors in abstractive summaries, 1, 10.18653/v1/2020.eval4nlp-1.1 · DOI · Paper page
- Nie, 2021, I like fish, especially dolphins: Addressing contradictions in dialogue modeling, 1699, 10.18653/v1/2021.acl-long.134 · DOI · Paper page
- van den Oord, 2018, Representation learning with contrastive predictive coding, CoRR
- Papineni, 2002, BLEU: A method for automatic evaluation of machine translation, 311, 10.3115/1073083.1073135 · DOI · Paper page
- Prabhumoye, 2021, Focused attention improves document-grounded generation, 4274, 10.18653/v1/2021.naacl-main.338 · DOI
- Radford, 2019, Language models are unsupervised multitask learners, OpenAI Blog, 1, 9
- Sipos, 2012, Large-margin learning of submodular summarization models, 224
- Stiles, 1992, Describing Talk: A Taxonomy of Verbal Response Modes
- Welleck, 2019, Dialogue natural language inference, 3731, 10.18653/v1/P19-1363 · DOI · Paper page
- Zhang, 2021, On the inductive bias of masked language modeling: From statistical to syntactic dependencies, 5131, 10.18653/v1/2021.naacl-main.404 · DOI
- Zhao, 2020, Knowledge-grounded dialogue generation with pre-trained language models, 3377, 10.18653/v1/2020.emnlp-main.272 · DOI · Paper page
- Zhou, 2018, A dataset for document grounded conversations, 708, 10.18653/v1/D18-1076 · DOI · Paper page
Cited by
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, W. X., Nie, J.-Y., & Wen, J.-R. (2023) · arXiv · doi:10.48550/arxiv.2305.11747 · Cited by 340
“For instance, The BEGIN benchmark (Dziri et al., 2022b) classifies the utterances generated by dialogue systems into three categories, i.e., fully attributable, not fully attributable, and generic; and the Attributable to Identified Sources (AIS) benchmark (Rashkin et al., 2021) assesses whether…”
BackgroundHaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, X., Nie, J.-Y., & Wen, J.-R. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.397 · Cited by 343
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Adlakha, V., BehnamGhader, P., Lu, X. H., Meade, N., & Reddy, S. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00667 · Cited by 74
“However, they struggle to be faithful to provided knowledge, often failing to accurately identify its relevance.”
BackgroundInfluentialSelf-citationEvaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Adlakha, V., BehnamGhader, P., Lu, X. H., Meade, N., & Reddy, S. (2023) · arXiv · doi:10.48550/arxiv.2307.16877 · Cited by 74
Self-citationEvaluating Attribution in Dialogue Systems: The BEGIN Benchmark
Dziri, N., Rashkin, H., Linzen, T., & Reitter, D. (2021) · arXiv · doi:10.48550/arxiv.2105.00071 · Cited by 47
Self-citation
Metadata
- Authors
- Dziri, N., Kamalloo, E., Milton, S., Zaiane, O., Yu, M., Ponti, E. M., & Reddy, S.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2022
- Volume
- 10
- Pages
- 1473-1490
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W4313459318
- Cited by
- 63
- References
- 42
- FWCI
- 3.96
- Type
- journal article
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.