6 citations · 12 across the 9 of their papers we have counts for
11 papers
The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs
Jiachen Zhao, Zhengxuan Wu, David Bau +1
Language models are routinely fine-tuned under a fixed context, such as a generic system prompt, persona or domain-specific instruction, yet the learned behavior sometimes stays co…
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
Xu Li, Simon Yu, Minzhou Pan +5
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in m…
SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models
Hamza Tahboub, Weiyan Shi, Gang Hua +1
Understanding social interactions from visual cues is a fundamental challenge for a socially competent AI. While powerful pre-trained vision-language models (VLMs) have shown remar…
Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA
Pu Zhao, Arash Akbari, Xuan Shen +16
Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are pro…
Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
Jiachen Zhao, Yiyou Sun, Weiyan Shi +1
Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the…
LLMs Encode Harmfulness and Refusal Separately
Jiachen Zhao, Jing Huang, Zhengxuan Wu +2
LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by…
Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects
Isabel O. Gallegos, Chen Shani, Weiyan Shi +4
As generative artificial intelligence (AI) enables the creation and dissemination of information at massive scale and speed, it is increasingly important to understand how people p…
Proactive Conversational Agents with Inner Thoughts
Xingyu Bruce Liu, Shitao Fang, Weiyan Shi +3
One of the long-standing aspirations in conversational AI is to allow them to autonomously take initiatives in conversations, i.e., being proactive. This is especially challenging…
Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval
Kazuaki Furumai, Roberto Legaspi, Julio Vizcarra +6
Persuasion plays a pivotal role in a wide range of applications from health intervention to the promotion of social good. Persuasive chatbots employed responsibly for social good c…
The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
Rongwu Xu, Brian S. Lin, Shujian Yang +6
Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility beha…