5 papers
Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting
Xu Zhang, Dev Mistry, Xiang Xu +1
In-context learning (ICL) jailbreaks reveal a critical vulnerability in multimodal large language models (MLLMs): harmful demonstrations in the prompt can induce unsafe outputs wit…
Temporal Dependencies in In-Context Learning: The Role of Induction Heads
Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini +3
Large language models (LLMs) exhibit strong in-context learning capabilities, but how they track and retrieve information from context remains underexplored. Drawing on the free re…
Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini +2
In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic m…
Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training
Deven Mahesh Mistry, Anooshka Bajaj, Yash Aggarwal +2
We investigate in-context temporal biases in attention heads and transformer outputs. Using cognitive science methodologies, we analyze attention scores and outputs of the GPT-2 mo…
A Comparative Study of Sentence Embedding Models for Assessing Semantic Variation
Deven M. Mistry, Ali A. Minai
Analyzing the pattern of semantic variation in long real-world texts such as books or transcripts is interesting from the stylistic, cognitive, and linguistic perspectives. It is a…