Papers by Advit Deepak
Enhancing Large Language Models through Transforming Reasoning Problems into Classification Tasks (2024.lrec-main)
Copied to clipboard
Tarun Raheja, Raunak Sinha, Advit Deepak, Will Healy, Jayanth Srinivasa, Myungjin Lee, Ramana Kompella
| Challenge: | Existing approaches to improve LLMs' reasoning capabilities for constraint satisfaction problems (CSPs) are needed to solve complex tasks. |
| Approach: | They propose a method that leverages the LLM's ability to decide when to call a function from a set of logical-linguistic primitives, each of which can interact with a local “scratchpad” memory and logical inference engine. |
| Outcome: | The proposed method improves the reasoning capabilities of large language models for constraint satisfaction problems by 40% over baselines. |
Identifying Unlearned Data in LLMs via Membership Inference Attacks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work evaluates approximate unlearning under a retrieval paradigm, where adversaries attempt to extract residual knowledge given partial information of the unlearning target. |
| Approach: | They propose a framework to evaluate unlearning membership attacks using member inference techniques to exploit the forget set. |
| Outcome: | The proposed framework assesses whether unlearning leaves behind detectable artifacts that can be exploited to infer membership in the forget set. |