Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculation...
Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing ...
This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of ...
Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM...
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined o...
AI technologies have rapidly moved into business and research applications that involve large text corpora, including computational journalism research and news...
Reward models (RMs) are essential for training large language models (LLMs), but remain underexplored for omni models that handle interleaved image and text seq...
Equipping large language models (LLMs) with search engines via reinforcement learning (RL) has emerged as an effective approach for building search agents. Howe...
Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challe...
Prosody -- the melody of speech -- conveys critical information often not captured by the words or text of a message. In this paper, we propose an information-t...
Choosing the number of topics T in Latent Dirichlet Allocation (LDA) is a key design decision that strongly affects both the statistical fit and interpretabilit...
Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure...
