4 papers
Steered LLM Activations are Non-Surjective
Aayush Mishra, Daniel Khashabi, Anqi Liu
Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in int…
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Aayush Mishra, Daniel Khashabi, Anqi Liu
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapt…
Genomic Next-Token Predictors are In-Context Learners
Nathan Breslow, Aayush Mishra, Mahler Revsine +3
In-context learning (ICL) -- the capacity of a model to infer and apply abstract patterns from examples provided within its input -- has been extensively studied in large language…
ICL CIPHERS: Quantifying "Learning" in In-Context Learning via Substitution Ciphers
Zhouxiang Fang, Aayush Mishra, Muhan Gao +2
Recent works have suggested that In-Context Learning (ICL) operates in dual modes, i.e. task retrieval (remember learned patterns from pre-training) and task learning (inference-ti…