4 papers
SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
Thinh Pham, Nguyen Nguyen, Pratibha Zunjare +3
We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful re…
: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models
Quyet V. Do, Thinh Pham, Nguyen Nguyen +3
We study a pipeline that curates reasoning data from initial structured data for improving long-context reasoning in large language models (LLMs). Our approach, , constructs…
NeuroProlog: Multi-Task Fine-Tuning for Neurosymbolic Mathematical Reasoning via the Cocktail Effect
Pratibha Zunjare, Michael Hsiao
Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently generating fluent yet logically incons…
A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences
Pratibha Zunjare, Michael Hsiao
This paper addresses the challenge of transforming complex sentences into sequences of logical, simplified sentences while preserving semantic and logical integrity with the help o…