20 citations · 20 across the 2 of their papers we have counts for
3 papers · 1 filter
ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models
Dhruv Dixit, Khushi Patel, Congcong Xu +1
Small language models are attractive for local, low-cost, and privacy-sensitive deployment, but they remain unreliable on mathematical reasoning tasks that require decomposition, e…
AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI
Snehalkumar `Neil' S. Gaikwad, Dhruv Dixit, Bryen Alvarez +4
Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question…
Self-Indexing Latent Memories for Access-Aware Continual Instruction Tuning of LLMs
Dhruv Dixit, Paritosh Pandey, Snehalkumar 'Neil' S. Gaikwad
Continual instruction tuning often preserves old skills with task-private modules. Inference still requires selecting the right module from the prompt alone. We introduce Task-Isol…