13 papers
Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning
Xinyu Luo, Hui Liu, Yihua Shao +3
The paper introduces Conditional Retrieval Alignment (CoRA), a gradient‑free method that turns a frozen encoder into a task‑conditioned retriever for on‑device in‑context learning,…
Unbiased Alignment for Large Language Models with Noisy Preferences
Jialiang Wang, Xianming Liu, Xiong Zhou +2
The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization. However, th…
Domain-Specific Data Generation Framework for RAG Adaptation
Chris Xing Tian, Weihao Xie, Zhen Chen +5
Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models (LLMs) with external retrieval to enable domain-grounded respo…
Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
Hui Liu, Bin Zou, Kecheng Chen +3
Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet u…
Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
Hui Liu, Kecheng Chen, Jialiang Wang +3
Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering an…
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +7
Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on lo…