Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
The paper introduces a novel reinforcement learning objective called Distribution-Aware Reward, aimed at improving predictive distributions in large language models for regression tasks. This method evaluates multiple decoded samples as an empirical predictive distribution, enhancing both accuracy and dispersion of predictions. The authors demonstrate that their approach outperforms traditional supervised fine-tuning and pointwise reinforcement learning across various tasks, leading to better uncertainty diagnostics and model robustness.
- ▪The method focuses on training language models to produce better predictive distributions rather than just optimizing individual outputs.
- ▪It evaluates decoded samples using the Continuous Ranked Probability Score and rewards predictions based on their contribution to distribution quality.
- ▪The approach shows significant improvements in rank correlation and remains competitive with advanced models in molecular property prediction.
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 →
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/2605.20740 |
| 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 | ueCuNq9BN5Gz |
| 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 > Machine Learning arXiv:2605.20740 (cs) [Submitted on 20 May 2026] Title:Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression Authors:Jungsoo Park, Hyungjoo Chae, Ethan Mendes, Jay DeYoung, Varsha Kishore, Wei Xu, Alan Ritter View a PDF of the paper titled Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression, by Jungsoo Park and 6 other authors View PDF HTML (experimental) Abstract:Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates without ensuring calibrated predictive distributions.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
