5 papers
Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
Zidi Xiong, Shan Chen, Himabindu Lakkaraju
As Large Reasoning Models (LRMs) are increasingly deployed, auditing their chain-of-thought (CoT) traces for safety becomes critical. Recent work has reported that monitorability--…
EvoLM: In Search of Lost Language Model Training Dynamics
Zhenting Qi, Fan Nie, Alexandre Alahi +6
Modern language model (LM) training has been divided into multiple stages, making it difficult for downstream developers to evaluate the impact of design choices made at each stage…
Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
Zidi Xiong, Shan Chen, Zhenting Qi +1
Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought exp…
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
Martin Pawelczyk, Lillian Sun, Zhenting Qi +2
The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong ge…
Quantifying Generalization Complexity for Large Language Models
Zhenting Qi, Hongyin Luo, Xuliang Huang +5
While large language models (LLMs) have shown exceptional capabilities in understanding complex queries and performing sophisticated tasks, their generalization abilities are often…