6 papers · 1 filter
FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions
Huaixia Dou, Jie Zhu, Minghao Wu +5
As large language models (LLMs) are increasingly deployed in financial services, a single non-compliant interaction can expose institutions to regulatory penalties and direct consu…
Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization
Weixuan Wang, Minghao Wu, Barry Haddow +1
Long document summarization remains a significant challenge for current large language models (LLMs), as existing approaches commonly struggle with information loss, factual incons…
HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models
Weixuan Wang, Minghao Wu, Barry Haddow +1
Fine-tuning large language models (LLMs) on a mixture of diverse datasets poses challenges due to data imbalance and heterogeneity. Existing methods often address these issues acro…
ExpertSteer: Intervening in LLMs through Expert Knowledge
Weixuan Wang, Minghao Wu, Barry Haddow +1
Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. A…
Demystifying Multilingual Chain-of-Thought in Process Reward Modeling
Weixuan Wang, Minghao Wu, Barry Haddow +1
Large language models (LLMs) are designed to perform a wide range of tasks. To improve their ability to solve complex problems requiring multi-step reasoning, recent research lever…
Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
Weixuan Wang, Minghao Wu, Barry Haddow +1
Large Language Models (LLMs) have shown remarkable capabilities in natural language processing but exhibit significant performance gaps among different languages. Most existing app…