4 papers
Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
Ngoc Trinh Hung Nguyen, Alonso Silva, Laith Zumot +3
Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely,…
Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering
Tejas Kulkarni, Antti Koskela, Laith Zumot
We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be vulnerable to membership-infer…
Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
João Paulo Nogueira, Wentao Sun, Alonso Silva +1
Large reasoning language models are typically run with fixed inference budgets, which can waste computation or terminate reasoning prematurely. We introduce Certainty-Guided Reason…
Differentially Private In-Context Learning with Nearest Neighbor Search
Antti Koskela, Tejas Kulkarni, Laith Zumot
Differentially private in-context learning (DP-ICL) has recently become an active research topic due to the inherent privacy risks of in-context learning. However, existing approac…