2 citations · 2 across the 5 of their papers we have counts for
6 papers
Smaller Models, Better Rejects: Preference Distillation Scaling
Rui Cai, Wenhui Zhu, Xiwen Chen +15
Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated failures are the most informat…
Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
Daiwei Chen, Zhoutong Fu, Chengming Jiang +12
Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in generative recommendation. The standar…
Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights
Yi Chen, Daiwei Chen, Sukrut Madhav Chikodikar +2
Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications. Retrieval-augmented generation (RAG) and conformal factuality h…
LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation
Haichao Zhang, Yao Lu, Lichen Wang +4
Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise on tasks such as movi…
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
Daiwei Chen, Yi Chen, Aniket Rege +1
Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically…
Learning Capacity: A Measure of the Effective Dimensionality of a Model
Daiwei Chen, Wei-Kai Chang, Pratik Chaudhari
We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning…