activity
20242026
collaborators

5 papers

cs.CL2026

Liars' Bench: Evaluating Lie Detectors for Language Models

Kieron Kretschmar, Walter Laurito, Sharan Maiya +1

Prior work has introduced techniques for detecting when large language models (LLMs) lie, that is, generate statements they believe are false. However, these techniques are typical…

cs.CL2025

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI

Sharan Maiya, Henning Bartsch, Nathan Lambert +1

The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These…

cs.CL2025

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

Yu Ying Chiu, Zhilin Wang, Sharan Maiya +4

Detecting AI risks becomes more challenging as stronger models emerge and find novel methods such as Alignment Faking to circumvent these detection attempts. Inspired by how risky…

cs.CL2025

Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes

Sharan Maiya, Yinhong Liu, Ramit Debnath +1

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear c…

cs.AI2024

Cluster-norm for Unsupervised Probing of Knowledge

Walter Laurito, Sharan Maiya, Grégoire Dhimoïla +3

The deployment of language models brings challenges in generating reliable information, especially when these models are fine-tuned using human preferences. To extract encoded know…