Papers › Neural Text Generation with Unlikelihood Training

Neural Text Generation with Unlikelihood Training

12 Aug 2019ICLR 2020 1arXiv:1908.04319archive 2025-07-28

Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, Jason Weston

Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some post-hoc fixes have been proposed, in particular top-k and nucleus sampling, they do not address the fact that the token-level probabilities predicted by the model are poor. In this paper we show that the likelihood objective itself is at fault, resulting in a model that assigns too much probability to sequences containing repeats and frequent words, unlike those from the human training distribution. We propose a new objective, unlikelihood training, which forces unlikely generations to be assigned lower probability by the model. We show that both token and sequence level unlikelihood training give less repetitive, less dull text while maintaining perplexity, giving superior generations using standard greedy or beam search. According to human evaluations, our approach with standard beam search also outperforms the currently popular decoding methods of nucleus sampling or beam blocking, thus providing a strong alternative to existing techniques.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1908.04319")

Code

Syntology Ran 6 of 6 code samples harvested from 5 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 5 samples from 4 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/unlikelihood_training officialmentioned in papermentioned on GitHubpytorch report
c00k1ez/plain-transformers mentioned on GitHubpytorch report
google/t5patches mentioned on GitHubjaxApache-2.0 report
griff4692/calibrating-summaries mentioned on GitHubjax report
ljyflores/loss-library mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 6 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
3ran · fixture could not drive it
2ran

Licence: 4 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

top_k_logits facebookresearch/unlikelihood_training/custom/sequence_generator.py official repository ran · fixture could not drive it fingerprinted licence not identified · pointer only · ace3f464bf5b4c7a · report
CandidateLoss fadedcosine/pos-guided-neural-text-generation/util/losses.py community (archive-listed) ran · metamorphic tier: invariant Apache-2.0 (permissive) · 785d35781789b4f4 · report
UnlikelihoodLoss c00k1ez/plain-transformers/src/plain_transformers/losses/unlikelihood_loss.py community (archive-listed) ran Apache-2.0 (permissive) · 1debde02b971ce55 · report
compute_unlikelihood_loss ljyflores/loss-library/src/loss_library/utils_unlikelihood_loss.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · bc59957c30488434 · report
label_smoothed_nll_loss griff4692/calibrating-summaries/model/contrast_utils.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · a261ba0741e044d7 · report
label_smoothed_unlikelihood griff4692/calibrating-summaries/model/contrast_utils.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 315417bd4bc9b0ad · report

Tasks

BlockingText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections