244 citations · 325 across the 22 of their papers we have counts for
21 papers · 1 filter
Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
Tsz Ting Chung, Leyang Cui, Lemao Liu +3
Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the add…
FuseChat: Knowledge Fusion of Chat Models
Fanqi Wan, Longguang Zhong, Ziyi Yang +2
While training large language models (LLMs) from scratch can indeed lead to models with distinct capabilities and strengths, it incurs substantial costs and may lead to redundancy…
On the Transformations across Reward Model, Parameter Update, and In-Context Prompt
Deng Cai, Huayang Li, Tingchen Fu +11
Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications. In this paper, we demonstra…
Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
Sen Yang, Leyang Cui, Deng Cai +3
Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to select worth-annotating resp…
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Xueliang Zhao, Xinting Huang, Tingchen Fu +5
Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs). The integration with Domain-Specific Languages (DSL), offering precise visual represen…
Knowledge Fusion of Chat LLMs: A Preliminary Technical Report
Fanqi Wan, Ziyi Yang, Longguang Zhong +3
Recently, FuseLLM introduced the concept of knowledge fusion to transfer the collective knowledge of multiple structurally varied LLMs into a target LLM through lightweight continu…
Knowledge Fusion of Large Language Models
Fanqi Wan, Xinting Huang, Deng Cai +3
While training large language models (LLMs) from scratch can generate models with distinct functionalities and strengths, it comes at significant costs and may result in redundant…
Inferflow: an Efficient and Highly Configurable Inference Engine for Large Language Models
Shuming Shi, Enbo Zhao, Deng Cai +3
We present Inferflow, an efficient and highly configurable inference engine for large language models (LLMs). With Inferflow, users can serve most of the common transformer models…
Knowledge Verification to Nip Hallucination in the Bud
Fanqi Wan, Xinting Huang, Leyang Cui +3
While large language models (LLMs) have demonstrated exceptional performance across various tasks following human alignment, they may still generate responses that sound plausible…
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration
Fanqi Wan, Xinting Huang, Tao Yang +3
Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks. However, existing data employed f…
SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving
Xueliang Zhao, Xinting Huang, Wei Bi +1
Large Language Models (LLMs) have driven substantial progress in artificial intelligence in recent years, exhibiting impressive capabilities across a wide range of tasks, including…
DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping
Yongrui Chen, Haiyun Jiang, Xinting Huang +2
The improvement of LLMs' instruction-following capabilities relies heavily on the availability of high-quality instruction-response pairs. Unfortunately, the current methods used t…
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Yue Zhang, Yafu Li, Leyang Cui +13
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit h…
Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration
Chenyang Lyu, Minghao Wu, Longyue Wang +5
Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text ha…
Pre-training Multi-party Dialogue Models with Latent Discourse Inference
Yiyang Li, Xinting Huang, Wei Bi +1
Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to…
Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance
Yue Zhang, Leyang Cui, Deng Cai +3
Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent st…
Effidit: Your AI Writing Assistant
Shuming Shi, Enbo Zhao, Duyu Tang +10
In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently…
Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering
Shiquan Yang, Xinting Huang, Jey Han Lau +1
Data artifacts incentivize machine learning models to learn non-transferable generalizations by taking advantage of shortcuts in the data, and there is growing evidence that data a…
Generalizable and Explainable Dialogue Generation via Explicit Action Learning
Xinting Huang, Jianzhong Qi, Yu Sun +1
Response generation for task-oriented dialogues implicitly optimizes two objectives at the same time: task completion and language quality. Conditioned response generation serves a…
Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation
Xinting Huang, Jianzhong Qi, Yu Sun +1
Dialogue policy optimization often obtains feedback until task completion in task-oriented dialogue systems. This is insufficient for training intermediate dialogue turns since sup…
MALA: Cross-Domain Dialogue Generation with Action Learning
Xinting Huang, Jianzhong Qi, Yu Sun +1
Response generation for task-oriented dialogues involves two basic components: dialogue planning and surface realization. These two components, however, have a discrepancy in their…