5 papers · 1 filter
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Krishak Aneja, Manas Mittal, Anmol Goel +2
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work lin…
From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences
Prashant Kodali, Anmol Goel, Likhith Asapu +5
Current computational approaches for analysing or generating code-mixed sentences do not explicitly model ``naturalness'' or ``acceptability'' of code-mixed sentences, but rely on…
InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?
Yogesh Tripathi, Raghav Donakanti, Sahil Girhepuje +7
Recent advancements in language technology and Artificial Intelligence have resulted in numerous Language Models being proposed to perform various tasks in the legal domain ranging…
HLDC: Hindi Legal Documents Corpus
Arnav Kapoor, Mudit Dhawan, Anmol Goel +7
Many populous countries including India are burdened with a considerable backlog of legal cases. Development of automated systems that could process legal documents and augment leg…
Are Models Trained on Indian Legal Data Fair?
Sahil Girhepuje, Anmol Goel, Gokul S Krishnan +4
Recent advances and applications of language technology and artificial intelligence have enabled much success across multiple domains like law, medical and mental health. AI-based…