87 citations · 108 across the 15 of their papers we have counts for
15 papers
Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
Zhihan Zhang, Tao Ge, Zhenwen Liang +5
Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks. To maximize such benefits, existing research focuses o…
Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
Mengzhao Jia, Zhihan Zhang, Wenhao Yu +2
Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, l…
PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning
Zhihan Zhang, Dong-Ho Lee, Yuwei Fang +4
Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions. Despite the success in high-resource language…
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Zhihan Zhang, Shuohang Wang, Wenhao Yu +6
Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning. Unfortunately, the pe…
Investigating Cross-Domain Behaviors of BERT in Review Understanding
Albert Lu, Meng Jiang
Review score prediction requires review text understanding, a critical real-world application of natural language processing. Due to dissimilar text domains in product reviews, a c…
Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions
Zhihan Zhang, Wenhao Yu, Zheng Ning +2
Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP. While studied in tasks such a…
IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions
Wenhao Yu, Meng Jiang, Peter Clark +1
Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult…
Improving Language Models via Plug-and-Play Retrieval Feedback
Wenhao Yu, Zhihan Zhang, Zhenwen Liang +2
Large language models (LLMs) exhibit remarkable performance across various NLP tasks. However, they often generate incorrect or hallucinated information, which hinders their practi…
Large Language Models are Built-in Autoregressive Search Engines
Noah Ziems, Wenhao Yu, Zhihan Zhang +1
Document retrieval is a key stage of standard Web search engines. Existing dual-encoder dense retrievers obtain representations for questions and documents independently, allowing…
Pre-training Language Models for Comparative Reasoning
Mengxia Yu, Zhihan Zhang, Wenhao Yu +1
Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a n…
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach
Wenhao Yu, Chenguang Zhu, Zhihan Zhang +4
A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and…
A Unified Encoder-Decoder Framework with Entity Memory
Zhihan Zhang, Wenhao Yu, Chenguang Zhu +1
Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks. We focus on incorporating entity knowledge into an encoder-decoder framework for informa…
Generate rather than Retrieve: Large Language Models are Strong Context Generators
Wenhao Yu, Dan Iter, Shuohang Wang +6
Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tas…
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
Zhihan Zhang, Wenhao Yu, Mengxia Yu +2
Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalitie…
Multi-Round Parsing-based Multiword Rules for Scientific OpenIE
Joseph Kuebler, Lingbo Tong, Meng Jiang
Information extraction (IE) in scientific literature has facilitated many down-stream tasks. OpenIE, which does not require any relation schema but identifies a relational phrase t…