6 citations · 33 across the 36 of their papers we have counts for
37 papers
From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers
Ji-Lun Peng, Yi-Zhen Zhang, Chun-Nan Chou +1
Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existing in-context learning-based me…
Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts
Yen-Ting Piao, Shu-Yun Chen, Chin-Hui Chu +4
Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-modal conflict remains underexplored. Existing benchmarks conf…
When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents
Wen-Yu Chang, Yun-Nung Chen
Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primar…
Joint Optimization of Tool Creation and Use for Large Language Model Agents
Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen +2
Tool-augmented language models are bounded by the APIs humans bothered to write; existing tool-creation systems patch this by prompting a frozen LLM at inference time, leaving the…
Avalon-ToM-Bench: Evaluating Fine-Grained Theory of Mind via Asymmetric Game Mechanics
Yen-Shan Chen, Yu Chian Duan, Chih-En Kuo +2
Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reasoning or interactive settings…
BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration
Yung-Yu Shih, Shang-Yu Su, Tzu-I Ho +2
E-commerce platforms in emerging markets often operate with underdeveloped product catalogs that contain only category taxonomies but lack structured attribute schemas. This absenc…
Rethinking Fairness in LLM-Based Recommender Systems: A Survey
Song-Duo Ma, Chu-Yun Chen, Bang-An Li +3
Large Language Models (LLMs) are reshaping recommender systems by enabling more semantic, generative, and interactive recommendation pipelines. However, this shift also introduces…
Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
Bo-Han Feng, Yu-Hsuan Li Liang, Chien-Feng Liu +2
Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced thro…
ICICLE: Expanding Retrieval with In-Context Documents
Yu-Chen Den, Yung-Yu Shih, Zhi Rui Tam +4
Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new document…
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. Wh…
Latent-Mark: An Audio Watermark Robust to Neural Codec Compression
Yen-Shan Chen, Shih-Yu Lai, Ying-Jung Tsou +5
While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural compressi…
Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects
Ji-Lun Peng, Yun-Nung Chen
Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs). However, current evaluation frameworks rely heavily on well-known fictional c…
AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
Tzu-Han Lin, Wei-Lin Chen, Chen-An Li +3
Equipping large language models (LLMs) with search engines via reinforcement learning (RL) promises effective search agents. However, adaptively balancing internal parametric knowl…
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su +4
Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical work…
Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1
Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase.…
Creativity in LLM-based Multi-Agent Systems: A Survey
Yi-Cheng Lin, Kang-Chieh Chen, Zhe-Yan Li +5
Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide compreh…
Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
Zhi Rui Tam, Cheng-Kuang Wu, Yi-Lin Tsai +3
Structured generation, the process of producing content in standardized formats like JSON and XML, is widely utilized in real-world applications to extract key output information f…
A Survey of Data Synthesis Approaches
Hsin-Yu Chang, Pei-Yu Chen, Tun-Hsiang Chou +4
This paper provides a detailed survey of synthetic data techniques. We first discuss the expected goals of using synthetic data in data augmentation, which can be divided into four…
Visualizing Dialogues: Enhancing Image Selection through Dialogue Understanding with Large Language Models
Chang-Sheng Kao, Yun-Nung Chen
Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than s…
I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation
Cheng-Kuang Wu, Zhi Rui Tam, Chao-Chung Wu +3
This study explores the proactive ability of LLMs to seek user support. We propose metrics to evaluate the trade-off between performance improvements and user burden, and investiga…
DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging
Tzu-Han Lin, Chen-An Li, Hung-yi Lee +1
Reinforcement learning from human feedback (RLHF) is a popular strategy for aligning large language models (LLMs) with desired behaviors. Reward modeling is a crucial step in RLHF.…
A Survey of Generative Information Retrieval
Tzu-Lin Kuo, Tzu-Wei Chiu, Tzung-Sheng Lin +3
Generative Retrieval (GR) is an emerging paradigm in information retrieval that leverages generative models to directly map queries to relevant document identifiers (DocIDs) withou…
A Survey of Useful LLM Evaluation
Ji-Lun Peng, Sijia Cheng, Egil Diau +4
LLMs have gotten attention across various research domains due to their exceptional performance on a wide range of complex tasks. Therefore, refined methods to evaluate the capabil…
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
Cheng-Kuang Wu, Zhi Rui Tam, Chieh-Yen Lin +2
Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deploym…