arXiv Machine Learning June 5, 2026 By Hyunji Nam, Haoran Li, Natasha Jaques

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 10

Peer-Predictive Self-Training for Language Model Reasoning

arXiv:2604. 13356v3 Announce Type: replace-cross Abstract: Mechanisms for continued self-improvement of language models without external supervision remain an open challenge.

By Shi Feng, Hanlin Zhang, Fan Nie, Sham Kakade, Yiling Chen

llms fine-tuning benchmarks

arXiv AI

Jun 2

Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization

arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.

By Hyung Gyu Rho

llms nlp reinforcement-learning

arXiv AI

Aug 11

Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning

arXiv:2608. 09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization.

By Yuting Liu, Wei Wu, Jianzhe Zhao, Guibing Guo

llms rag agents reinforcement-learning

arXiv AI

Jul 3

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

arXiv:2607. 02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain.

By Zhuowei Chen, Xiang Lorraine Li

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jun 24

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

arXiv:2509. 03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models.

By Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Simon Fu, Narmeen Oozeer

llms safety

arXiv Machine Learning

Jun 2

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

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.

By Hasan Amin, Kian Ahrabian, Ming Yin, Rajiv Khanna

llms fine-tuning multimodal benchmarks

Related stories

Peer-Predictive Self-Training for Language Model Reasoning

Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization

Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

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