76 citations · 89 across the 13 of their papers we have counts for
7 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…
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1
As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While uncertainty quantification is w…
Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds
Anish R Joishy, Ishwar B Balappanawar, Vamshi Krishna Bonagiri +3
A fundamental challenge in reasoning is navigating hypothetical, counterfactual worlds where logic may conflict with ingrained knowledge. We investigate this frontier for Large Lan…
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…
SaGE: Evaluating Moral Consistency in Large Language Models
Vamshi Krishna Bonagiri, Sreeram Vennam, Priyanshul Govil +2
Despite recent advancements showcasing the impressive capabilities of Large Language Models (LLMs) in conversational systems, we show that even state-of-the-art LLMs are morally in…
Measuring Moral Inconsistencies in Large Language Models
Vamshi Krishna Bonagiri, Sreeram Vennam, Manas Gaur +1
A Large Language Model (LLM) is considered consistent if semantically equivalent prompts produce semantically equivalent responses. Despite recent advancements showcasing the impre…
COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models
Priyanshul Govil, Hemang Jain, Vamshi Krishna Bonagiri +4
Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating th…