5 papers
ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering
Shubhra Ghosh, Abhilekh Borah, Aditya Kumar Guru +1
The rapid proliferation of Large Language Models (LLMs) has significantly contributed to the development of equitable AI systems capable of factual question-answering (QA). However…
Don't Judge a Book by its Cover: Testing LLMs' Robustness Under Logical Obfuscation
Abhilekh Borah, Shubhra Ghosh, Kedar Joshi +2
Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in their standard form, but they oft…
ReGal: A First Look at PPO-based Legal AI for Judgment Prediction and Summarization in India
Shubham Kumar Nigam, Tanuj Tyagi, Siddharth Shukla +6
This paper presents an early exploration of reinforcement learning methodologies for legal AI in the Indian context. We introduce Reinforcement Learning-based Legal Reasoning (ReGa…
QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
Danush Khanna, Aditya Kumar Guru, Srivarshinee Sridhar +7
Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency h…
SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
Danush Khanna, Pratinav Seth, Sidhaarth Sredharan Murali +5
Mental manipulation is a subtle yet pervasive form of abuse in interpersonal communication, making its detection critical for safeguarding potential victims. However, due to manipu…