llm-personalization

Tag

Cards List
#llm-personalization

Re-Centering Humans in LLM Personalization

arXiv cs.CL · 2026-06-08 Cached

This paper studies the gap between synthetic and human data for evaluating LLM personalization across three stages: attribute extraction, relevance matching, and response generation. Results show models perform worse on real human data, and the authors introduce lightweight training interventions to improve alignment.

0 favorites 0 likes
#llm-personalization

Re-Centering Humans in LLM Personalization

Hugging Face Daily Papers · 2026-06-04 Cached

This paper investigates the effectiveness of LLM personalization by putting real humans back into the evaluation loop, revealing systematic gaps between human judgments and LLM outputs at every stage of the personalization pipeline, and highlighting the limitations of synthetic data and LLM judges.

0 favorites 0 likes
#llm-personalization

Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation

arXiv cs.CL · 2026-05-26 Cached

This paper proposes PUMA, a framework for LLM personalization in multi-turn conversations that models latent user states and uses the Free Energy Principle to select dialogue actions, improving long-horizon outcomes on healthcare counseling benchmarks.

0 favorites 0 likes
#llm-personalization

Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures

arXiv cs.LG · 2026-05-13 Cached

This paper introduces Test-Time Personalization (TTP), a framework that improves LLM personalization by scaling inference-time computation through candidate sampling and reward-based selection. It diagnoses failure modes in standard reward models and proposes a probabilistic personalized reward model to mitigate them.

0 favorites 0 likes
#llm-personalization

Beyond Static Personas: Situational Personality Steering for Large Language Models

arXiv cs.CL · 2026-04-20 Cached

This paper introduces IRiS, a training-free framework for situational personality steering in LLMs that moves beyond static persona modeling by identifying and leveraging situation-dependent persona neurons. The approach demonstrates that LLM behavior varies contextually and proposes neuron-based identification, retrieval, and weighted steering methods validated on PersonalityBench and a new SPBench benchmark.

0 favorites 0 likes
← Back to home

Submit Feedback