collaborators

5 papers

cs.LG2026

Broken Chains: The Cost of Incomplete Reasoning in LLMs

Ian Su, Gaurav Purushothaman, Jey Narayan +5

Reasoning-specialized models like OpenAI's 5.1 and DeepSeek-V3.2 allocate substantial inference compute to extended chain-of-thought (CoT) traces, yet reasoning tokens incur signif…

cs.AI2025

Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving

Anisha Garg, Engin Tekin, Yash More +3

Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Exp…

cs.CR2025

Towards More Realistic Extraction Attacks: An Adversarial Perspective

Yash More, Prakhar Ganesh, Golnoosh Farnadi

Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single…

cs.CL2025

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset

Khaoula Chehbouni, Jonathan Colaço Carr, Yash More +2

In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards outputs that are intended to be both less…

cs.AI2025

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs

Megh Thakkar, Quentin Fournier, Matthew Riemer +4

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these…