29 citations · 33 across the 5 of their papers we have counts for
7 papers
Resisting Harmful Instructions through Training-Free Weight Editing
Ali Ebrahimpour-Boroojeny, Xiaocong Yang, Samuel Schapiro +4
Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free weight-editing approach for…
Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files
Xiaocong Yang, Rishit Chatterjee, Himanshu Udupi +2
A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patching an iss…
LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever
Xiaocong Yang
Modern dense information retrieval (IR) models usually rely on costly large-scale pretraining. In this paper, we introduce LLM2IR, an efficient unsupervised contrastive learning fr…
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
Xiaocong Yang, Jiacheng Lin, Ziqi Wang +1
Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structur…
Cascade Speculative Drafting for Even Faster LLM Inference
Ziyi Chen, Xiaocong Yang, Jiacheng Lin +3
Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then r…
Parameter-Efficient Tuning with Special Token Adaptation
Xiaocong Yang, James Y. Huang, Wenxuan Zhou +1
Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we on…
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Hao Zhou, Pei Ke, Zheng Zhang +11
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue dat…