5 papers
EKLAV: Elicited Key CoT Learning via Answer only superVision
Adarsh Singh, Aman Singh, Kushal Raj Bhandari +4
Reasoning distillation trains a student to reproduce both the teacher's chain-of-thought trace and its final answer. We ask whether the trace is better used as privileged training…
Invariant Reasoning Directions in Latent Trajectories of Language Models
Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut +3
Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains poorly understood. We show tha…
Improving Robustness of Tabular Retrieval via Representational Stability
Kushal Raj Bhandari, Adarsh Singh, Jianxi Gao +2
Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization even when table semantics remain…
RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tables
Nikhil Abhyankar, Purvi Chaurasia, Sanchit Kabra +3
Existing tabular reasoning benchmarks mostly test models on small, uniform tables, underrepresenting the complexity of real-world data and giving an incomplete view of Large Langua…
Distribution Shift Aware Neural Tabular Learning
Wangyang Ying, Nanxu Gong, Dongjie Wang +5
Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data.…