5 papers
LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning
Quang Hieu Pham, Thuy Duong Nguyen, Jocelyn Qiaochu Chen +1
Language-model (LM) harnesses enable LMs to operate effectively over long contexts using additional compute. However, existing long-context evaluations are insufficient for disting…
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
Quang Hieu Pham, Yang He, Ping Nie +5
Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Most current systems follow a…
Detecting and Suppressing Reward Hacking with Gradient Fingerprints
Songtao Wang, Quang Hieu Pham, Fangcong Yin +4
Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptib…
ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations
Quang Hieu Pham, Thuy Duong Nguyen, Tung Pham +2
The capabilities of large language models (LLMs) have been enhanced by training on data that reflects human thought processes, such as the Chain-of-Thought format. However, evidenc…
Who's Who: Large Language Models Meet Knowledge Conflicts in Practice
Quang Hieu Pham, Hoang Ngo, Anh Tuan Luu +1
Retrieval-augmented generation (RAG) methods are viable solutions for addressing the static memory limits of pre-trained language models. Nevertheless, encountering conflicting sou…