5 citations · 11 across the 6 of their papers we have counts for
7 papers
CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing
Rui Wang, Junda Wu, Yu Xia +6
Large Language Models (LLMs) are susceptible to indirect prompt injection attacks, where the model inadvertently responds to instructions injected into the prompt context. This vul…
Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
Chengkai Huang, Junda Wu, Yu Xia +9
Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems that extend beyond the capabilities of standalone models. By empowering LLMs to…
Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
Zhendong Chu, Ruiyi Zhang, Tong Yu +4
To achieve state-of-the-art performance, one still needs to train NER models on large-scale, high-quality annotated data, an asset that is both costly and time-intensive to accumul…
InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
Junda Wu, Tong Yu, Rui Wang +6
Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of…
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning
Kaige Xie, Tong Yu, Haoliang Wang +6
In real-world scenarios, labeled samples for dialogue summarization are usually limited (i.e., few-shot) due to high annotation costs for high-quality dialogue summaries. To effici…
Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
Tong Yu, Branislav Kveton, Zheng Wen +2
We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent vari…
Reward Constrained Interactive Recommendation with Natural Language Feedback
Ruiyi Zhang, Tong Yu, Yilin Shen +3
Text-based interactive recommendation provides richer user feedback and has demonstrated advantages over traditional interactive recommender systems. However, recommendations can e…