3 papers
cs.AI2026
TopoTuner: Topological Finetuning of Large Language Models
Abdulkadir Erol, Yash Mahajan, Vepaul Hariprashad +4
Full fine-tuning remains a strong way to adapt pretrained LLMs, but it updates all weights and can be expensive. LoRA reduces the number of trainable parameters, but it does not di…
cs.CL2025
Revisiting Word Embeddings in the LLM Era
Yash Mahajan, Matthew Freestone, Sathyanarayanan Aakur +1
Large Language Models (LLMs) have recently shown remarkable advancement in various NLP tasks. As such, a popular trend has emerged lately where NLP researchers extract word/sentenc…
cs.CL2025
Set-Theoretic Compositionality of Sentence Embeddings
Naman Bansal, Yash mahajan, Sanjeev Sinha +1
Sentence encoders play a pivotal role in various NLP tasks; hence, an accurate evaluation of their compositional properties is paramount. However, existing evaluation methods predo…