3 papers
cs.CL2026
Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models
Xiangming Gu, Soham De, Larisa Markeeva +2
Large Reasoning Models (LRMs) have shown remarkable performance on challenging questions, such as math and coding. However, to obtain a high quality solution, one may need to sampl…
cs.AI2025
Extracting alignment data in open models
Federico Barbero, Xiangming Gu, Christopher A. Choquette-Choo +6
In this work, we show that it is possible to extract significant amounts of alignment training data from a post-trained model -- useful to steer the model to improve certain capabi…
cs.CL2025
Why do LLMs attend to the first token?
Federico Barbero, Ãlvaro Arroyo, Xiangming Gu +4
Large Language Models (LLMs) tend to attend heavily to the first token in the sequence -- creating a so-called attention sink. Many works have studied this phenomenon in detail, pr…