7 papers · 1 filter
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Jacob Dineen, Aswin RRV, Zhikun Xu +1
Co-evolutionary self-play, where one language model generates problems and another solves them, promises curriculum learning without human supervision. The promise breaks down earl…
QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
Jacob Dineen, Aswin RRV, Qin Liu +8
Alignment of large language models (LLMs) with principles like helpfulness, honesty, and harmlessness typically relies on scalar rewards that obscure which objectives drive the tra…
PHANTOM RECALL: When Familiar Puzzles Fool Smart Models
Souradeep Mukhopadhyay, Rishabh Baral, Nimeesh Mahajan +5
Large language models (LLMs) such as GPT, Gemini, and Claude often appear adept at solving classic logic puzzles--but how much genuine reasoning underlies their answers? Recent evi…
Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
Amir Saeidi, Shivanshu Verma, Aswin RRV +2
Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference…
ToW: Thoughts of Words Improve Reasoning in Large Language Models
Zhikun Xu, Ming Shen, Jacob Dineen +6
We introduce thoughts of words (ToW), a novel training-time data-augmentation method for next-word prediction. ToW views next-word prediction as a core reasoning task and injects f…
Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
Nemika Tyagi, Mihir Parmar, Mohith Kulkarni +5
Solving grid puzzles involves a significant amount of logical reasoning. Hence, it is a good domain to evaluate the reasoning capability of a model which can then guide us to impro…