Comparison of Diverse Decoding Methods from Conditional Language Models
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
While conditional language models have greatly improved in their ability to output high-quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences.Diverse decoding strategies aim to, within a givensized candidate list, cover as much of the space of high-quality outputs as possible, leading to improvements for tasks that re-rank and combine candidate outputs.Standard decoding methods, such as beam search, optimize for generating high likelihood sequences rather than diverse ones, though recent work has focused on increasing diversity in these methods.In this work, we perform an extensive survey of decoding-time strategies for generating diverse outputs from conditional language models.We also show how diversity can be improved without sacrificing quality by oversampling additional candidates, then filtering to the desired number.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, R., Zhou, B., dos Santos, C., Gulcehre, C., & Xiang, B. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1028 · Cited by 2,361
Vinyals, O., & Le, Q. (2015) · arXiv · doi:10.48550/arxiv.1506.05869 · Cited by 1,400
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266 · cited 3×
“Random Sampling Another option is to randomly sample from the model’s distribution at every timestep.”
BackgroundHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
Creative Writing with a Machine in the Loop: Case Studies on Slogans and Stories
Clark, E., Ross, A. S., Tan, C., Ji, Y., & Smith, N. A. (2018) · 23rd International Conference on Intelligent User Interfaces · doi:10.1145/3172944.3172983 · Cited by 257 · cited 1×
“For example, in collaborative story generation, the system makes suggestions to a user for what they should write next (Clark et al., 2018).”
BackgroundUnifying Human and Statistical Evaluation for Natural Language Generation
Hashimoto, T. B., Zhang, H., & Liang, P. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1169 · Cited by 161
Cited by
Towards a Human-like Open-Domain Chatbot
Adiwardana, D., Luong, M.-T., So, D. R., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., Lu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2001.09977 · Cited by 614
“Many works, e.g., Zhao et al. (2017); Xu et al. (2018); Ippolito et al. (2019b), have focused solely on the diversity aspect to counter the commonly observed problem of models generating generic responses (Li et al., 2016a).”
BackgroundAdvances and challenges in conversational recommender systems: A survey
Gao, C., Lei, W., He, X., de Rijke, M., & Chua, T.-S. (2021) · AI Open · doi:10.1016/j.aiopen.2021.06.002 · Cited by 337
Homogenization Effects of Large Language Models on Human Creative Ideation
Anderson, B. R., Shah, J. H., & Kreminski, M. (2024) · Creativity and Cognition · doi:10.1145/3635636.3656204 · Cited by 188
Sparks: Inspiration for Science Writing using Language Models
Gero, K. I., Liu, V., & Chilton, L. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533533 · Cited by 161
“Despite their successes, language models continue to exhibit known problems, such as generic outputs [26], lack of diversity in their outputs [28], and factually false or contradictory information [35].”
BackgroundOn Decoding Strategies for Neural Text Generators
Wiher, G., Meister, C., & Cotterell, R. (2022) · arXiv · doi:10.48550/arxiv.2203.15721 · Cited by 48
Metadata
- Authors
- Ippolito, D., Kriz, R., Sedoc, J., Kustikova, M., & Callison-Burch, C.
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 3752-3762
- OpenAlex
- W2951038425
- Cited by
- 92
- References
- 8
- FWCI
- 5.91
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Comparison of Diverse Decoding Methods from Conditional Language Models. https://app.cochat.ai/papers/10.18653/v1/p19-1365
- The paper
- Ippolito, D., Kriz, R., Sedoc, J., Kustikova, M., & Callison-Burch, C. (2019). Comparison of Diverse Decoding Methods from Conditional Language Models. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1365
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.