arXiv Machine Learning June 2, 2026 By Hasan Amin, Kian Ahrabian, Ming Yin, Rajiv Khanna

Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization

Read the original on arXiv Machine Learning →

arXiv:2606. 00544v1 Announce Type: new Abstract: Modern language-model fine-tuning typically pairs each prompt with a single response, even though many prompts admit multiple valid completions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 17

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

arXiv:2510. 01171v4 Announce Type: replace-cross Abstract: Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse.

By Jiayi Zhang, Simon Yu, Derek Chong, Anthony Sicilia, Michael R. Tomz, Christopher D. Manning, Weiyan Shi

llms safety

arXiv Machine Learning

Jun 5

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data

arXiv:2603. 19294v4 Announce Type: replace Abstract: While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers.

By Hyunji Nam, Haoran Li, Natasha Jaques

llms nlp

arXiv AI

Jul 7

Demonstrating Generalization Failures via Mixtures of Conditional Policies

arXiv:2607. 03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments.

By Jou Barzdukas, Jack Peck, Julian Schulz, Paulius Rauba, Steven Basart, Lennie Wells

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 22

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.

By Alexander Manev

llms reinforcement-learning robotics benchmarks safety

arXiv Machine Learning

Jul 7

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.

By Yueyang Wang, Baolong Bi, Shuo Lu, Jingyuan Zhang

llms fine-tuning multimodal

arXiv AI

Sep 15

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

arXiv:2609.14896v1 Announce Type: cross Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infer...

By Jiayi Yuan, Hangoo Kang, James Jihao Liu, Yejin Choi, Vikram Iyer, Liwei Jiang, Natasha Jaques

llms agents reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data

Demonstrating Generalization Failures via Mixtures of Conditional Policies

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning