69 citations · 248 across the 38 of their papers we have counts for
38 papers
Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
Cheng Wang, Qin Liu, Wenxuan Zhou +1
Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectivel…
OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas
James Y. Huang, Wenxuan Zhou, Nan Xu +5
The ability of Large Language Models (LLMs) to generate structured outputs that follow arbitrary schemas is crucial to a wide range of downstream tasks that require diverse structu…
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +5
Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studie…
Code Execution as Grounded Supervision for LLM Reasoning
Dongwon Jung, Wenxuan Zhou, Muhao Chen
Training large language models (LLMs) with chain-of-thought (CoT) supervision has proven effective for enhancing their reasoning abilities. However, obtaining reliable and accurate…
MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
Qin Liu, Wenxuan Zhou, Nan Xu +5
One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively sel…
Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection
Bangzheng Li, Fei Wang, Wenxuan Zhou +5
Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large languag…
ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
Xiaofei Wen, Wenxuan Zhou, Wenjie Jacky Mo +1
Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass cla…
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Fei Wang, Xingyu Fu, James Y. Huang +18
We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs. MuirBench consists of 12 diverse multi-image tas…
mDPO: Conditional Preference Optimization for Multimodal Large Language Models
Fei Wang, Wenxuan Zhou, James Y. Huang +4
Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios…
WPO: Enhancing RLHF with Weighted Preference Optimization
Wenxuan Zhou, Ravi Agrawal, Shujian Zhang +5
Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization,…
Offset Unlearning for Large Language Models
James Y. Huang, Wenxuan Zhou, Fei Wang +4
Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as c…
Contrastive Instruction Tuning
Tianyi Lorena Yan, Fei Wang, James Y. Huang +5
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks. However, current LLMs exhibit limited robustnes…
GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding
Zekun Li, Wenxuan Zhou, Yao-Yi Chiang +1
Humans subconsciously engage in geospatial reasoning when reading articles. We recognize place names and their spatial relations in text and mentally associate them with their phys…
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
Wenxuan Zhou, Sheng Zhang, Yu Gu +2
Large language models (LLMs) have demonstrated remarkable generalizability, such as understanding arbitrary entities and relations. Instruction tuning has proven effective for dist…
Robust Natural Language Understanding with Residual Attention Debiasing
Fei Wang, James Y. Huang, Tianyi Yan +2
Natural language understanding (NLU) models often suffer from unintended dataset biases. Among bias mitigation methods, ensemble-based debiasing methods, especially product-of-expe…
Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
Tianqing Fang, Zhaowei Wang, Wenxuan Zhou +3
Event temporal reasoning aims at identifying the temporal relations between two or more events from narratives. However, knowledge conflicts arise when there is a mismatch between…
A Causal View of Entity Bias in (Large) Language Models
Fei Wang, Wenjie Mo, Yiwei Wang +2
Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired met…
How Fragile is Relation Extraction under Entity Replacements?
Yiwei Wang, Bryan Hooi, Fei Wang +6
Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE…
Context-faithful Prompting for Large Language Models
Wenxuan Zhou, Sheng Zhang, Hoifung Poon +1
Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametri…
Continual Contrastive Finetuning Improves Low-Resource Relation Extraction
Wenxuan Zhou, Sheng Zhang, Tristan Naumann +2
Relation extraction (RE), which has relied on structurally annotated corpora for model training, has been particularly challenging in low-resource scenarios and domains. Recent lit…
Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Keming Lu, I-Hung Hsu, Wenxuan Zhou +2
Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of…
On-the-fly Denoising for Data Augmentation in Natural Language Understanding
Tianqing Fang, Wenxuan Zhou, Fangyu Liu +3
Data Augmentation (DA) is frequently used to provide additional training data without extra human annotation automatically. However, data augmentation may introduce noisy data that…
Parameter-Efficient Tuning with Special Token Adaptation
Xiaocong Yang, James Y. Huang, Wenxuan Zhou +1
Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we on…
GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction
Yiwei Wang, Muhao Chen, Wenxuan Zhou +3
Entity types and textual context are essential properties for sentence-level relation extraction (RE). Existing work only encodes these properties within individual instances, whic…