Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP
The paper discusses a novel approach to uncertainty decomposition in subjective natural language processing (NLP). It integrates soft-label learning with Bayesian deep learning to assess annotator disagreement in emotion classification. The proposed method demonstrates improved performance on the GoEmotions benchmark compared to existing techniques.
- ▪The study focuses on annotator disagreement in emotion classification, which reflects intrinsic ambiguity in emotion concepts.
- ▪The authors propose a method that combines cyclical stochastic gradient Markov chain Monte Carlo with soft-label learning.
- ▪Results show that the new method outperforms Monte Carlo Dropout and Deep Ensemble on multiple evaluation axes.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.24773 |
| Publication time | Tue, 26 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-26T04:07:43.013Z |
| Last seen | 2026-05-26T04:07:43.013Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | tUNkLHdcA27n |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.24773 (cs) [Submitted on 23 May 2026] Title:Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP Authors:Keito Inoshita, Takato Ueno View a PDF of the paper titled Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP, by Keito Inoshita and 1 other authors View PDF HTML (experimental) Abstract:Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in subjective NLP. Yet no prior work integrates soft-label learning with Bayesian deep learning to evaluate uncertainty along axes including annotator-distribution fidelity.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
