3 citations · 3 across the 10 of their papers we have counts for
11 papers
LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers
Jingyu Hu, Shu Yang, Weiru Liu +1
Chain-of-Thought (CoT) reasoning has been shown to improve the performance of large language models (LLMs), yet existing optimization methods largely rely on outcome-based feedback…
AdaHAT: Adaptive Hard Attention to the Task in Task-Incremental Learning
Pengxiang Wang, Hongbo Bo, Jun Hong +2
Catastrophic forgetting is a major problem in task-incremental learning, where neural networks tend to overwrite previously learned knowledge when trained on new tasks. A number of…
StakeBench: Evaluating Language Understanding Grounded in Market Commitment
Yunhua Pei, Jingyu Hu, Yiwei Shi +3
Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuring how language is perceived rather than what speakers have committed to in the market.…
Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
Hongbo Bo, Jingyu Hu, Weiru Liu
Large Language Models (LLMs) have emerged as a new paradigm for multi-agent systems. However, existing research on the behaviour of LLM-based multi-agents relies on ad hoc prompts…
Failing on Bias Mitigation: A Case Study on the Challenges of Fairness in Government Data
Hongbo Bo, Jingyu Hu, Debbie Watson +1
The potential for bias and unfairness in AI-supporting government services raises ethical and legal concerns. Using crime rate prediction with the Bristol City Council data as a ca…
MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
Jingyu Hu, Shu Yang, Xilin Gong +3
Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent…
Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
Jingyu Hu, Hongbo Bo, Jun Hong +2
Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks, where prediction performance varies across nodes with different degrees. Several approaches…
Fine-Grained Interpretation of Political Opinions in Large Language Models
Jingyu Hu, Mengyue Yang, Mengnan Du +1
Studies of LLMs' political opinions mainly rely on evaluations of their open-ended responses. Recent work indicates that there is a misalignment between LLMs' responses and their i…
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
Dong Shu, Haiyan Zhao, Jingyu Hu +4
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment betwe…
ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups
Jingyu Hu, Jun Hong, Mengnan Du +1
Many bias mitigation methods have been developed for addressing fairness issues in machine learning. We found that using linear mixup alone, a data augmentation technique, for bias…
Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
Jingyu Hu, Weiru Liu, Mengnan Du
Recent studies highlight the effectiveness of using in-context learning (ICL) to steer large language models (LLMs) in processing tabular data, a challenging task given the structu…