2 papers
cs.CL2026
RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
Kyle Whitecross, Negin Rahimi
We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from…
cs.LG2024
Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise
Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
Increasing the size of overparameterized neural networks has been a key in achieving state-of-the-art performance. This is captured by the double descent phenomenon, where the test…