30 citations · 75 across the 25 of their papers we have counts for
25 papers
REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features
Kai-Xuan Ding, Hao-Xiang Xu, Ji-Hua Peng +3
Steering with Sparse Autoencoders (SAEs) offers a lightweight inference-time path for adapting the behavior of large language models without retraining. By exposing sparse and inte…
Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens
Shi-Qi Yan, Kai-Xuan Ding, Chao-Hong Tan +4
The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from language models. However, its principle and meaning lack a detailed and theoretical…
Multiplicative Orthogonal Sequential Editing for Language Models
Hao-Xiang Xu, Jun-Yu Ma, Ziqi Peng +3
Knowledge editing aims to efficiently modify the internal knowledge of large language models (LLMs) without compromising their other capabilities. The prevailing editing paradigm,…
Constraining Sequential Model Editing with Editing Anchor Compression
Hao-Xiang Xu, Jun-Yu Ma, Zhen-Hua Ling +2
Large language models (LLMs) struggle with hallucinations due to false or outdated knowledge. Given the high resource demands of retraining these models, there is an increasing foc…
Perturbation-Restrained Sequential Model Editing
Jun-Yu Ma, Hong Wang, Hao-Xiang Xu +2
Model editing is an emerging field that focuses on updating the knowledge embedded within large language models (LLMs) without extensive retraining. However, current model editing…
Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval
Qian Wang, Jia-Chen Gu, Zhen-Hua Ling
Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typi…
Neighboring Perturbations of Knowledge Editing on Large Language Models
Jun-Yu Ma, Zhen-Hua Ling, Ningyu Zhang +1
Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature…
Corrective Retrieval Augmented Generation
Shi-Qi Yan, Jia-Chen Gu, Yun Zhu +1
Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although…
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma +4
Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining. While current mod…
Is ChatGPT a Good Multi-Party Conversation Solver?
Chao-Hong Tan, Jia-Chen Gu, Zhen-Hua Ling
Large Language Models (LLMs) have emerged as influential instruments within the realm of natural language processing; nevertheless, their capacity to handle multi-party conversatio…
Evaluating the Reversal Curse in Model Editing
Hao-Xiang Xu, Jun-Yu Ma, Zhen-Hua Ling +3
Large language models (LLMs) are prone to hallucinate unintended text due to false or outdated knowledge. Since retraining LLMs is resource intensive, there has been a growing inte…
SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction
Jun-Yu Ma, Jia-Chen Gu, Zhen-Hua Ling +3
Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource lang…
DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion
Chao-Hong Tan, Jia-Chen Gu, Zhen-Hua Ling
Diffusion models have emerged as the new state-of-the-art family of deep generative models, and their promising potentials for text generation have recently attracted increasing at…
Pre-training Language Model as a Multi-perspective Course Learner
Beiduo Chen, Shaohan Huang, Zihan Zhang +6
ELECTRA, the generator-discriminator pre-training framework, has achieved impressive semantic construction capability among various downstream tasks. Despite the convincing perform…
USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER
Jun-Yu Ma, Jia-Chen Gu, Jiajun Qi +3
This paper describes the system developed by the USTC-NELSLIP team for SemEval-2023 Task 2 Multilingual Complex Named Entity Recognition (MultiCoNER II). A method named Statistical…
MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
Jia-Chen Gu, Chao-Hong Tan, Caiyuan Chu +4
Modeling multi-party conversations (MPCs) with graph neural networks has been proven effective at capturing complicated and graphical information flows. However, existing methods r…
GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding
Jia-Chen Gu, Zhen-Hua Ling, Quan Liu +2
Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understand…
WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition
Jun-Yu Ma, Beiduo Chen, Jia-Chen Gu +5
Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data…
USTC-NELSLIP at SemEval-2022 Task 11: Gazetteer-Adapted Integration Network for Multilingual Complex Named Entity Recognition
Beiduo Chen, Jun-Yu Ma, Jiajun Qi +3
This paper describes the system developed by the USTC-NELSLIP team for SemEval-2022 Task 11 Multilingual Complex Named Entity Recognition (MultiCoNER). We propose a gazetteer-adapt…
TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge
Chao-Hong Tan, Jia-Chen Gu, Chongyang Tao +5
Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various…
HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations
Jia-Chen Gu, Chao-Hong Tan, Chongyang Tao +4
Recently, various response generation models for two-party conversations have achieved impressive improvements, but less effort has been paid to multi-party conversations (MPCs) wh…
Detecting Speaker Personas from Conversational Texts
Jia-Chen Gu, Zhen-Hua Ling, Yu Wu +3
Personas are useful for dialogue response prediction. However, the personas used in current studies are pre-defined and hard to obtain before a conversation. To tackle this issue,…
SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning
Boyuan Zheng, Xiaoyu Yang, Yu-Ping Ruan +4
This paper introduces the SemEval-2021 shared task 4: Reading Comprehension of Abstract Meaning (ReCAM). This shared task is designed to help evaluate the ability of machines in re…
Promoting Diversity for End-to-End Conversation Response Generation
Yu-Ping Ruan, Zhen-Hua Ling, Quan Liu +2
We present our work on Track 2 in the Dialog System Technology Challenges 7 (DSTC7). The DSTC7-Track 2 aims to evaluate the response generation of fully data-driven conversation mo…