一作ACL 2026Poster· Natural Language Processing
Pref- CTRL : Preference Driven LLM Alignment using Representation Editing
Imranul Ashrafi · Inigo Jauregi Unanue · Massimo Piccardi
摘要
Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on their internal representations. Recently, a prominent and effective approach, RE-Control (Kong et al., 2024), has pr...