Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs
Aakriti Shah, Yifan Hu, Thai Le
Unlearning in large language models (LLMs) is usually evaluated as whether an "unlearned" fact can be recovered. We instead ask whether a fact's structural entanglement with the re…
cs.CL2025
Sample-Efficient Language Model for Hinglish Conversational AI
Sakshi Singh, Abhinav Prakash, Aakriti Shah +2
This paper presents our process for developing a sample-efficient language model for a conversational Hinglish chatbot. Hinglish, a code-mixed language that combines Hindi and Engl…