26 citations · 67 across the 45 of their papers we have counts for
19 papers · 1 filter
Context-DPO: Aligning Language Models for Context-Faithfulness
Baolong Bi, Shaohan Huang, Yiwei Wang +11
Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intenti…
RedStone: Curating General, Code, Math, and QA Data for Large Language Models
Yaoyao Chang, Lei Cui, Li Dong +13
Pre-training Large Language Models (LLMs) on high-quality, meticulously curated datasets is widely recognized as critical for enhancing their performance and generalization capabil…
MH-MoE: Multi-Head Mixture-of-Experts
Shaohan Huang, Xun Wu, Shuming Ma +1
Multi-Head Mixture-of-Experts (MH-MoE) demonstrates superior performance by using the multi-head mechanism to collectively attend to information from various representation spaces…
Textual Aesthetics in Large Language Models
Lingjie Jiang, Shaohan Huang, Xun Wu +1
Image aesthetics is a crucial metric in the field of image generation. However, textual aesthetics has not been sufficiently explored. With the widespread application of large lang…
Direct Preference Knowledge Distillation for Large Language Models
Yixing Li, Yuxian Gu, Li Dong +3
In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, exis…
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Daixuan Cheng, Yuxian Gu, Shaohan Huang +3
Unsupervised multitask pre-training has been the critical method behind the recent success of language models (LMs). However, supervised multitask learning still holds significant…
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Ting Jiang, Shaohan Huang, Shengyue Luo +8
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA…
You Only Cache Once: Decoder-Decoder Architectures for Language Models
Yutao Sun, Li Dong, Yi Zhu +6
We introduce a decoder-decoder architecture, YOCO, for large language models, which only caches key-value pairs once. It consists of two components, i.e., a cross-decoder stacked u…
Semi-Parametric Retrieval via Binary Bag-of-Tokens Index
Jiawei Zhou, Li Dong, Furu Wei +1
Information retrieval has transitioned from standalone systems into essential components across broader applications, with indexing efficiency, cost-effectiveness, and freshness be…
Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation
Xun Wu, Shaohan Huang, Furu Wei
Recent studies have demonstrated the exceptional potentials of leveraging human preference datasets to refine text-to-image generative models, enhancing the alignment between gener…
Multi-Head Mixture-of-Experts
Xun Wu, Shaohan Huang, Wenhui Wang +1
Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activat…
Mixture of LoRA Experts
Xun Wu, Shaohan Huang, Furu Wei
LoRA has gained widespread acceptance in the fine-tuning of large pre-trained models to cater to a diverse array of downstream tasks, showcasing notable effectiveness and efficienc…
Towards Optimal Learning of Language Models
Yuxian Gu, Li Dong, Yaru Hao +3
This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance.…
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
Shuhua Shi, Shaohan Huang, Minghui Song +7
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs). However, updati…
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition
Yuxuan Liu, Tianchi Yang, Shaohan Huang +6
Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations. However, the alignment and coverage of LLM-based evaluations are often limited…
Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
Haoran Li, Qingxiu Dong, Zhengyang Tang +17
We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs). Unlike prior work that relies on se…
Text Diffusion with Reinforced Conditioning
Yuxuan Liu, Tianchi Yang, Shaohan Huang +6
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a st…
: Sequential Example Selection for In-Context Learning
Haoyu Liu, Jianfeng Liu, Shaohan Huang +5
The remarkable capability of large language models (LLMs) for in-context learning (ICL) needs to be activated by demonstration examples. Prior work has extensively explored the sel…
Improving Domain Adaptation through Extended-Text Reading Comprehension
Ting Jiang, Shaohan Huang, Shengyue Luo +8
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method. Recent work demonstrates that adapti…