6 papers
Measuring Weak-to-Strong Legibility of Reasoning Models
Dani Roytburg, Shreya Sridhar, Daphne Ippolito
Reasoning language models (RLMs) and the intermediate chains of thought they emit play an increasingly central role in multi-agent setups such as inter-model monitoring or distilla…
No Single Best Model for Diversity: Learning a Router for Sample Diversity
Yuhan Liu, Fangyuan Xu, Vishakh Padmakumar +2
When posed with prompts that permit a large number of valid answers, comprehensively generating them is the first step towards satisfying a wide range of users. In this paper, we s…
Think Before You Lie: How Reasoning Leads to Honesty
Ann Yuan, Asma Ghandeharioun, Carter Blum +6
While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investi…
On Code-Induced Reasoning in LLMs
Abdul Waheed, Zhen Wu, Carolyn Rosé +1
Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate th…
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
Shivalika Singh, Angelika Romanou, Clémentine Fourrier +21
Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from differences in language but also…
Consent in Crisis: The Rapid Decline of the AI Data Commons
Shayne Longpre, Robert Mahari, Ariel Lee +46
General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we…