2 citations · 4 across the 9 of their papers we have counts for
3 papers · 2 filters
GAPS: Dimension-Level Gates for Conditional Activation Steering
Moghis Fereidouni, Muhammad Umair Haider, Hassan Sajjad +1
Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditional methods such as CAST and…
Persona-Guided LLM Agents for Task-Oriented Dialogue
Maryam Shoaeinaeini, Brent Harrison, A. B. Siddique
Prior work has shown that large language models can express diverse personality traits in open-ended text generation, but it is unclear whether they can do so in goal-directed dial…
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
Sing Hieng Wong, Hassan Sajjad, A. B. Siddique
Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresse…