4 papers · 1 filter
Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States
Subramanyam Sahoo, Vinija Jain, Aman Chadha +1
Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types. We test this by probing…
Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity
Subramanyam Sahoo, Vinija Jain, Saanidhya Vats +4
Current evaluation of mathematical reasoning in language models relies primarily on answer accuracy, potentially masking fundamental failures in logical computation. We introduce a…
Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization
Sahil Wadhwa, Chengtian Xu, Haoming Chen +3
The automatic generation of counter-speech (CS) is a critical strategy for addressing hate speech by providing constructive and informed responses. However, existing methods often…
SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval
Aakash Mahalingam, Vinesh Kumar Gande, Aman Chadha +2
Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucination…