← Search

Shirish Karande

2 accepted papers

2026

The Realignment Problem: When Right becomes Wrong in LLMs

ICML 2026poster

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make static alignment increasingly brittle. As policies evolve, deploy…

Cited by 0SourceScholar
2025

Nine Ways to Break Copyright Law and Why Our LLM Won’t: A Fair Use Aligned Generation Framework

EMNLP 2025

Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time safeguards predominantly rely on restrictive refusal-based

Cited by 0SourcePDFScholar