3 papers
cs.LG2026
Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RL
Amit Nautiyal
When reinforcement learning teaches a language model a new behavior, can we find the training rollouts that taught it? And when an attribution method says it can, how do we know th…
cs.LG2026
Traceprop: Training Data Attribution in a Single Pass
Amit Nautiyal
Data attribution tools used in practice, TRAK, LoGRA/LogIX, and EK-FAC, run after training: they recompute per-sample gradients in a separate pass over the training set, and curvat…
cs.CL2026
ChunkRank: Model-Aware Text Chunking and Abstention-Aware Answer Selection for LLM Pipelines
Amit Nautiyal, Ayush Bhatt, Gaurav Nautiyal
We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an answer among candidates produce…