36 citations · 393 across the 141 of their papers we have counts for
26 papers · 1 filter
Enhancing AI Safety Through the Fusion of Low Rank Adapters
Satya Swaroop Gudipudi, Sreeram Vipparla, Harpreet Singh +2
Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models gen…
KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
Thilini Wijesiriwardene, Ruwan Wickramarachchi, Sreeram Vennam +5
Making analogies is fundamental to cognition. Proportional analogies, which consist of four terms, are often used to assess linguistic and cognitive abilities. For instance, comple…
A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
Varshita Kolipaka, Akshit Sinha, Debangan Mishra +4
Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distri…
Rethinking Thinking Tokens: Understanding Why They Underperform in Practice
Sreeram Vennam, David Valente, David Herel +1
Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs m…
LLM Vocabulary Compression for Low-Compute Environments
Sreeram Vennam, Anish Joishy, Ponnurangam Kumaraguru
We present a method to compress the final linear layer of language models, reducing memory usage by up to 3.4x without significant performance loss. By grouping tokens based on Byt…
Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes
Rahul Garg, Trilok Padhi, Hemang Jain +2
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). I…