55 citations · 83 across the 14 of their papers we have counts for
14 papers
DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation
He Wang, Alexander Hanbo Li, Yiqun Hu +6
Large language model (LLM) agents have shown promising performance in generating code for solving complex data science problems. Recent studies primarily focus on enhancing in-cont…
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects
Naihao Deng, Sheng Zhang, Henghui Zhu +7
Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly the paradox of choice: the diffic…
PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries
Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu +9
Previous text-to-SQL datasets and systems have primarily focused on user questions with clear intentions that can be answered. However, real user questions can often be ambiguous w…
Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall
Jiaqing Yuan, Lin Pan, Chung-Wei Hang +5
Large language models (LLMs) have shown remarkable performance on a variety of NLP tasks, and are being rapidly adopted in a wide range of use cases. It is therefore of vital impor…
Benchmarking Diverse-Modal Entity Linking with Generative Models
Sijia Wang, Alexander Hanbo Li, Henry Zhu +9
Entities can be expressed in diverse formats, such as texts, images, or column names and cell values in tables. While existing entity linking (EL) models work well on per modality…
UNITE: A Unified Benchmark for Text-to-SQL Evaluation
Wuwei Lan, Zhiguo Wang, Anuj Chauhan +15
A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively e…
Importance of Synthesizing High-quality Data for Text-to-SQL Parsing
Yiyun Zhao, Jiarong Jiang, Yiqun Hu +14
Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and di…
Improved Text Classification via Contrastive Adversarial Training
Lin Pan, Chung-Wei Hang, Avirup Sil +1
We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks. Specifically, during fine-tuning we generate adver…
Multilingual BERT Post-Pretraining Alignment
Lin Pan, Chung-Wei Hang, Haode Qi +3
We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Usi…
Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis
Zhe Zhang, Chung-Wei Hang, Munindar P. Singh
Sentiments in opinionated text are often determined by both aspects and target words (or targets). We observe that targets and aspects interrelate in subtle ways, often yielding co…
The Causal Link between News Framing and Legislation
Karthik Sheshadri, Chung-Wei Hang, Munindar Singh
We demonstrate that framing, a subjective aspect of news, is a causal precursor to both significant public perception changes, and to federal legislation. We posit, counter-intuiti…
Framing Matters: Predicting Framing Changes and Legislation from Topic News Patterns
Karthik Sheshadri, Chung-Wei Hang, Munindar Singh
News has traditionally been well researched, with studies ranging from sentiment analysis to event detection and topic tracking. We extend the focus to two surprisingly under-resea…
Empirical Study on Deep Learning Models for Question Answering
Yang Yu, Wei Zhang, Chung-Wei Hang +2
In this paper we explore deep learning models with memory component or attention mechanism for question answering task. We combine and compare three models, Neural Machine Translat…
A Probabilistic Approach for Maintaining Trust Based on Evidence
Yonghong Wang, Chung-Wei Hang, Munindar P. Singh
Leading agent-based trust models address two important needs. First, they show how an agent may estimate the trustworthiness of another agent based on prior interactions. Second, t…