Interpretable Discriminative Text Representations via Agreement and Label Disentanglement
The paper presents a new method for creating interpretable text representations that are both predictive and meaningful. It introduces LLM-assisted Feature Discovery (LFD), which enhances feature clarity and reduces label entanglement. The results demonstrate that LFD achieves high agreement among human annotators and maintains predictive performance across various text classification tasks.
- ▪The proposed method focuses on conceptual clarity and label disentanglement in text representations.
- ▪LLM-assisted Feature Discovery (LFD) screens features using cross-LLM Cohen's kappa for reliability.
- ▪LFD features show higher agreement and are judged as less label-leaking compared to baseline concepts.
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/2605.20693 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| 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 | l5Gft_2Hdwh2 |
| 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 > Computation and Language arXiv:2605.20693 (cs) [Submitted on 20 May 2026] Title:Interpretable Discriminative Text Representations via Agreement and Label Disentanglement Authors:Tong Wang, Yiqing Xu, Leo Yang Yang View a PDF of the paper titled Interpretable Discriminative Text Representations via Agreement and Label Disentanglement, by Tong Wang and 2 other authors View PDF HTML (experimental) Abstract:Interpretable text representations should expose coordinates that are not only predictive, but also meaningful enough for independent auditors to apply.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
