From the 1 of 36 linked papers with an AI index.
36 papers
Can Argus Judge Them All? Comparing VLMs Across Domains
Harsh Joshi, Gautam Siddharth Kashyap, Rafiq Ali +5
The paper introduces ARGUS-EVAL, a framework that assesses vision-language models on both capability and reliability across domains, and uses it to compare several VLMs on retrieva…
ChildGuard: A Specialized Dataset for Combatting Child-Targeted Hate Speech
Gautam Siddharth Kashyap, Mohammad Anas Azeez, Rafiq Ali +3
Mental health industry faces growing concerns regarding hate speech directed at children's on social media, as exposure to such content can contribute to adverse psychological outc…
Truth, Trust, and Trouble: Medical AI on the Edge
Mohammad Anas Azeez, Rafiq Ali, Ebad Shabbir +4
Large Language Models (LLMs) hold significant promise for transforming digital health by enabling automated medical question answering. However, ensuring these models meet critical…
Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
Utsav Maskey, Chencheng Zhu, Usman Naseem
Recent advancements in large language models (LLMs) have transformed natural language understanding and generation, leading to extensive benchmarking across diverse tasks. However,…
Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
Utsav Maskey, Mark Dras, Usman Naseem
Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natura…
We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong
Gautam Siddharth Kashyap, Mark Dras, Usman Naseem
Alignment of Large Language Models (LLMs) is the ability to satisfy desired objectives during generation, which is critical for trustworthy deployment. In practice, alignment is of…