15 citations · 64 across the 39 of their papers we have counts for
40 papers
ProgAgent: Learning Tool Orchestration through Programmatic Training
Hao Li, Keqing He, Longtao Zheng +4
Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where the mode…
AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming
Muxi Diao, Yutao Mou, Keqing He +6
The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on seed instructions, which limits…
Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
Weihao Zeng, Keqing He, Chuqiao Kuang +2
Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and sel…
AgentRefine: Enhancing Agent Generalization through Refinement Tuning
Dayuan Fu, Keqing He, Yejie Wang +7
Large Language Model (LLM) based agents have proved their ability to perform complex tasks like humans. However, there is still a large gap between open-sourced LLMs and commercial…
Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
Siqi Wang, Zhengyu Chen, Bei Li +3
The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment. Our work investigates the transferabi…
How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
Yejie Wang, Keqing He, Dayuan Fu +11
Recently, there has been a growing interest in studying how to construct better code instruction tuning data. However, we observe Code models trained with these datasets exhibit hi…
DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
Weihao Zeng, Dayuan Fu, Keqing He +3
Language models pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of task-oriented dialogues (TOD) compar…
Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
Pei Wang, Keqing He, Yejie Wang +6
Out-of-domain (OOD) intent detection aims to examine whether the user's query falls outside the predefined domain of the system, which is crucial for the proper functioning of task…
BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
Weihao Zeng, Keqing He, Yejie Wang +2
Pre-trained language models have been successful in many scenarios. However, their usefulness in task-oriented dialogues is limited due to the intrinsic linguistic differences betw…
Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models
Pei Wang, Yejie Wang, Muxi Diao +3
In the deployment of large language models (LLMs), accurate confidence estimation is critical for assessing the credibility of model predictions. However, existing methods often fa…
Knowledge Editing on Black-box Large Language Models
Xiaoshuai Song, Zhengyang Wang, Keqing He +4
Knowledge editing (KE) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowl…
DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
Yejie Wang, Keqing He, Guanting Dong +8
Code Large Language Models (Code LLMs) have demonstrated outstanding performance in code-related tasks. Several instruction tuning approaches have been proposed to boost the code g…
PreAct: Prediction Enhances Agent's Planning Ability
Dayuan Fu, Jianzhao Huang, Siyuan Lu +4
Addressing the disparity between forecasts and actual results can enable individuals to expand their thought processes and stimulate self-reflection, thus promoting accurate planni…
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Wei Liu, Weihao Zeng, Keqing He +2
Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. Recent research indicates…
APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Pei Wang, Keqing He, Yutao Mou +6
Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system. Previous OOD detection studies generally work on the assumption that plent…
Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition
Xiaoshuai Song, Yutao Mou, Keqing He +3
In a practical dialogue system, users may input out-of-domain (OOD) queries. The Generalized Intent Discovery (GID) task aims to discover OOD intents from OOD queries and extend th…
Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT
Xiaoshuai Song, Keqing He, Pei Wang +6
The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to tas…
Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task
Guanting Dong, Jinxu Zhao, Tingfeng Hui +8
With the increasing capabilities of large language models (LLMs), these high-performance models have achieved state-of-the-art results on a wide range of natural language processin…
Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
Jiachi Liu, Liwen Wang, Guanting Dong +8
In real dialogue scenarios, as there are unknown input noises in the utterances, existing supervised slot filling models often perform poorly in practical applications. Even though…
A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
Guanting Dong, Zechen Wang, Jinxu Zhao +10
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional…
Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting
Xuefeng Li, Liwen Wang, Guanting Dong +5
Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source domain to the unlabeled target domain. Existing models either encode slot descriptions and ex…
Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation
Weihao Zeng, Lulu Zhao, Keqing He +4
Existing controllable dialogue generation work focuses on the single-attribute control and lacks generalization capability to out-of-distribution multiple attribute combinations. I…
FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue
Weihao Zeng, Keqing He, Yejie Wang +4
Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-orien…
GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model
Shicheng Tan, Weng Lam Tam, Yuanchun Wang +9
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment…