4 citations · 10 across the 12 of their papers we have counts for
13 papers
One Probe Won't Catch Them All: Towards Targeted Deception Detection
Vikram Natarajan, Devina Jain, Shivam Arora +2
Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair…
Auditing Games for Sandbagging
Jordan Taylor, Sid Black, Dillon Bowen +10
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagging detection techni…
ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction
Aly Lidayan, Jakob Bjorner, Satvik Golechha +2
As the time horizons of sequential decision-making tasks grow, keeping full interaction histories in model context becomes increasingly costly. Recent work reduces context lengths…
Who's the Evil Twin? Differential Auditing for Undesired Behavior
Ishwar Balappanawar, Venkata Hasith Vattikuti, Greta Kintzley +2
Detecting hidden behaviors in neural networks poses a significant challenge due to minimal prior knowledge and potential adversarial obfuscation. We explore this problem by framing…
Among Us: A Sandbox for Measuring and Detecting Agentic Deception
Satvik Golechha, Adrià Garriga-Alonso
Prior studies on deception in language-based AI agents typically assess whether the agent produces a false statement about a topic, or makes a binary choice prompted by a goal, rat…
Auditing language models for hidden objectives
Samuel Marks, Johannes Treutlein, Trenton Bricken +32
We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…
Studying Cross-cluster Modularity in Neural Networks
Satvik Golechha, Maheep Chaudhary, Joan Velja +2
An approach to improve neural network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We define a measure…
Training Neural Networks for Modularity aids Interpretability
Satvik Golechha, Dylan Cope, Nandi Schoots
An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models t…
Progress Measures for Grokking on Real-world Tasks
Satvik Golechha
Grokking, a phenomenon where machine learning models generalize long after overfitting, has been primarily observed and studied in algorithmic tasks. This paper explores grokking i…
NICE: To Optimize In-Context Examples or Not?
Pragya Srivastava, Satvik Golechha, Amit Deshpande +1
Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of t…
CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients
Pragnya Ramjee, Bhuvan Sachdeva, Satvik Golechha +4
The healthcare landscape is evolving, with patients seeking reliable information about their health conditions and available treatment options. Despite the abundance of information…
Challenges in Mechanistically Interpreting Model Representations
Satvik Golechha, James Dao
Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and…
Predicting Treatment Adherence of Tuberculosis Patients at Scale
Mihir Kulkarni, Satvik Golechha, Rishi Raj +9
Tuberculosis (TB), an infectious bacterial disease, is a significant cause of death, especially in low-income countries, with an estimated ten million new cases reported globally i…