From the 1 of 4 linked papers with an AI index.
4 papers
The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics
Shashwat Sourav, Aishwarya Balwani
Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process. Existing approaches…
Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models
Antyabha Rahman, Akshaj Gurugubelli, Omar Ankit +2
The paper investigates why reinforcement‑learning‑trained models outperform supervised fine‑tuned models on math reasoning by analyzing their internal representations with linear p…
ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
Manasi Sharma, Chen Bo Calvin Zhang, Chaithanya Bandi +13
Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities,…
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
Daniel Aarao Reis Arturi, Eric Zhang, Andrew Ansah +3
Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent m…