9 citations · 31 across the 34 of their papers we have counts for
35 papers
UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization
Viet-Thanh Pham, Thuy-Trang Vu, Junae Kim +4
Guardrail models are increasingly used as safety layers for LLMs and agentic systems, but most are trained on fixed prompt or response interfaces and become unreliable when the sam…
Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees
Shuo Huang, Gholamreza Haffari, Xingliang Yuan +2
Empirical identity leakage from released text is increasingly driven by attackers that combine large language models (LLMs) with auxiliary knowledge to link documents to individual…
MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models
Manh Luong, Tamas Abraham, Junae Kim +6
Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text. We introduce MCBench,…
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction…
Resurfacing Paralinguistic Awareness in Large Audio Language Models
Hao Yang, Minghan Wang, Tongtong Wu +3
Large Audio Language Models (LALMs) have expanded the interaction with human to speech modality, which introduces great interactive potential, due to the paralinguistic cues implic…
LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations
Viet-Thanh Pham, Lizhen Qu, Thuy-Trang Vu +2
Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator relia…
IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
Tao Feng, Lizhen Qu, Niket Tandon +1
Causal discovery is fundamental to scientific research, yet traditional statistical algorithms face significant challenges, including expensive data collection, redundant computati…
Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search
Shuo Huang, Xingliang Yuan, Gholamreza Haffari +1
The increasing adoption of large language models (LLMs) in cloud-based services has raised significant privacy concerns, as user inputs may inadvertently expose sensitive informati…
Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation
Tao Feng, Xianbing Zhao, Zhenhua Chen +4
Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignm…
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models
Hao Yang, Lizhen Qu, Ehsan Shareghi +1
Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed…
RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
Yuncheng Hua, Lizhen Qu, Zhuang Li +3
Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant…
Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
Manh Luong, Khai Nguyen, Dinh Phung +2
Audio captioning systems face a fundamental challenge: teacher-forcing training creates exposure bias that leads to caption degeneration during inference. While contrastive methods…
Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
Hao Yang, Lizhen Qu, Ehsan Shareghi +1
Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to…
Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
Hao Yang, Lizhen Qu, Ehsan Shareghi +1
Large language models (LLMs) have exhibited outstanding performance in engaging with humans and addressing complex questions by leveraging their vast implicit knowledge and robust…
Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights
Hao Yang, Lizhen Qu, Ehsan Shareghi +1
Large Multimodal Models (LMMs) have achieved great success recently, demonstrating a strong capability to understand multimodal information and to interact with human users. Despit…
CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems
Tao Feng, Lizhen Qu, Xiaoxi Kang +1
Automatically evaluating the quality of responses in open-domain dialogue systems is a challenging but crucial task. Current evaluation metrics often fail to align with human judgm…
Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction
Yuncheng Hua, Yujin Huang, Shuo Huang +5
This paper tackles the task of emotion-cause pair extraction in the unsupervised domain adaptation setting. The problem is challenging as the distributions of the events causing em…
SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
Zhuang Li, Yuncheng Hua, Thuy-Trang Vu +3
Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tun…
Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models
Minghao Wu, Thuy-Trang Vu, Lizhen Qu +1
Large language models (LLMs) are typically fine-tuned on diverse and extensive datasets sourced from various origins to develop a comprehensive range of skills, such as writing, re…
NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Shuo Huang, William MacLean, Xiaoxi Kang +5
The widespread use of cloud-based Large Language Models (LLMs) has heightened concerns over user privacy, as sensitive information may be inadvertently exposed during interactions…
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
Manh Luong, Khai Nguyen, Nhat Ho +3
The Learning-to-match (LTM) framework proves to be an effective inverse optimal transport approach for learning the underlying ground metric between two sources of data, facilitati…
IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models
Tao Feng, Lizhen Qu, Zhuang Li +3
Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains. This study focuses on a specific problem of domain gene…
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Haolan Zhan, Yufei Wang, Tao Feng +7
Negotiation is a crucial ability in human communication. Recently, there has been a resurgent research interest in negotiation dialogue systems, whose goal is to create intelligent…
Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues
Yuncheng Hua, Lizhen Qu, Gholamreza Haffari
We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations. Specifically, we simulate business negotiations by letting two LL…