6 papers · 1 filter
Psychologically-Grounded Graph Modeling for Interpretable Depression Detection
Rishitej Reddy Vyalla, Kritarth Prasad, Avinash Anand +4
Automatic depression detection from conversational interactions holds significant promise for scalable screening but remains hindered by severe data scarcity and a lack of clinical…
IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical Reasoning
Navya Gupta, Rishitej Reddy Vyalla, Avinash Anand +8
Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consistent step-by-step reasoning, e…
Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5
Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formali…
Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
Nirmalendu Prakash, Yeo Wei Jie, Amir Abdullah +3
Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study…
Understanding Refusal in Language Models with Sparse Autoencoders
Wei Jie Yeo, Nirmalendu Prakash, Clement Neo +3
Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in…
Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
Wei Jie Yeo, Ranjan Satapathy, Erik Cambria
Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations sho…