neuron-analysis

Tag

Cards List
#neuron-analysis

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
#neuron-analysis

MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation

Hugging Face Daily Papers · 2026-04-18 Cached

MNAFT (Modality Neuron-Aware Fine-Tuning) is a novel approach that selectively updates language-specific and language-agnostic neurons in multimodal large language models to improve image translation while preserving pre-trained knowledge. The method outperforms state-of-the-art image translation techniques including cascaded models and standard fine-tuning approaches.

0 favorites 0 likes
← Back to home

Submit Feedback