Maximizing mutual information between user-contexts and responses improve LLM personalization with no additional data

• URL: http://arxiv.org/abs/2603.19294v1
• Date: Tue, 10 Mar 2026 21:00:05 GMT
• Title: Maximizing mutual information between user-contexts and responses improve LLM personalization with no additional data
• Abstract summary: We propose a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioning on the correct prompt, and a negative response by conditioning on a random, unrelated prompt.<n>We show that using Direct Preference Optimization (DPO) to learn from this paired data maximizes pointwise conditional mutual information (MI) between prompts and model responses.<n>Surprisingly, MIPO can also be applied to improve performance on math and multiple-choice problems, yielding 1-18% **without any additional data or human supervision.
• Score: 12.193946608981276
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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. Existing data has already been exploited, and new high-quality data is expensive to collect. More fundamentally, true intelligence goes far beyond tasks that are easily verifiable. Therefore, we need self-improvement frameworks that allow models to improve without external oversight. We propose *Mutual Information Preference Optimization (MIPO)*, a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioning on the correct prompt, and a negative response by conditioning on a random, unrelated prompt. We show that using Direct Preference Optimization (DPO) to learn from this paired data maximizes pointwise conditional mutual information (MI) (under the base LLM) between prompts and model responses. Empirical results with various-sized Llama- and Qwen-Instruct models show that when used to maximize MI between user context and response, MIPO provides an effective personalization technique, achieving 3-40% improvements on personalization tasks using real-user datasets compared to strong baselines. Surprisingly, MIPO can also be applied to improve performance on math and multiple-choice problems, yielding 1-18% **without any additional data or human supervision**. These results suggest a promising direction for self-improvement.

Related papers

• Towards Understanding Valuable Preference Data for Large Language Model Alignment [85.38864561060088]
  Large language model (LLM) alignment is typically achieved through learning from human preference comparisons.<n>We assess data quality through individual influence on validation data using our newly proposed truncated influence function (TIF)<n>To this end, we combine them to offset their diverse error sources, resulting in a simple yet effective data selection rule.
  arXiv  Detail & Related papers  (2025-10-15T06:57:55Z)
• Aligning Large Language Models via Fully Self-Synthetic Data [20.05693955243206]
  Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets.<n>In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment.<n>Experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval2.0.
  arXiv  Detail & Related papers  (2025-10-08T05:07:45Z)
• SGPO: Self-Generated Preference Optimization based on Self-Improver [6.528083376369728]
  Large language models (LLMs) require alignment to human preferences for practical and reliable deployment.<n>We propose Self-Generated Preference Optimization based on Self-Improver (SGPO)<n>The improver refines responses from a policy model to self-generate preference data for direct preference optimization (DPO) of the policy model.<n> Experimental results on AlpacaEval 2.0 and Arena-Hard show that the proposed SGPO significantly improves performance over DPO and baseline self-improving methods.
  arXiv  Detail & Related papers  (2025-07-27T08:55:40Z)
• Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining [75.14823970163685]
  We propose a novel preference learning framework, Modality-Balancing Preference Optimization (MBPO), to address the modality imbalance in LMMs.<n>MBPO constructs a more effective offline preference dataset by generating hard negatives, i.e., rejected responses misled by LLM biases.<n>It can enhance LMM performance on challenging vision-language tasks and effectively reduce hallucinations.
  arXiv  Detail & Related papers  (2025-05-20T03:59:05Z)
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection [68.8373788348678]
  Visual instruction tuning adapts pre-trained Multimodal Large Language Models to follow human instructions.<n>PRISM is the first training-free framework for efficient visual instruction selection.<n>It reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-17T18:43:41Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)
• Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective [4.548047308860141]
  This study investigates the impact of different type of preference data on model performance. It aims to reduce their dependency on extensive amounts of preference data, which is expensive to collect.
  arXiv  Detail & Related papers  (2024-10-22T00:11:41Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.<n>We show that our approach consistently boosts DPO by a considerable margin.<n>Our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Enabling Language Models to Implicitly Learn Self-Improvement [49.16868302881804]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. We propose an ImPlicit Self-ImprovemenT (PIT) framework that implicitly learns the improvement goal from human preference data.
  arXiv  Detail & Related papers  (2023-10-02T04:29:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.