31 citations · 41 across the 11 of their papers we have counts for
8 papers · 1 filter
Quantifying Generalization Complexity for Large Language Models
Zhenting Qi, Hongyin Luo, Xuliang Huang +5
While large language models (LLMs) have shown exceptional capabilities in understanding complex queries and performing sophisticated tasks, their generalization abilities are often…
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Zhenting Qi, Mingyuan Ma, Jiahang Xu +3
This paper introduces rStar, a self-play mutual reasoning approach that significantly improves reasoning capabilities of small language models (SLMs) without fine-tuning or superio…
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
Zhenting Qi, Hanlin Zhang, Eric Xing +2
Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore le…
RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations
Yilun Zhao, Chen Zhao, Linyong Nan +5
Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task…
QTSumm: Query-Focused Summarization over Tabular Data
Yilun Zhao, Zhenting Qi, Linyong Nan +9
People primarily consult tables to conduct data analysis or answer specific questions. Text generation systems that can provide accurate table summaries tailored to users' informat…
LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control
Yilun Zhao, Zhenting Qi, Linyong Nan +2
Logical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables. There currently exists two challenges in the field: 1) Faithfulness: how…
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
Yilun Zhao, Linyong Nan, Zhenting Qi +2
Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training…
FOLIO: Natural Language Reasoning with First-Order Logic
Simeng Han, Hailey Schoelkopf, Yilun Zhao +32
Large language models (LLMs) have achieved remarkable performance on a variety of natural language understanding tasks. However, existing benchmarks are inadequate in measuring the…