61 citations · 135 across the 32 of their papers we have counts for
32 papers
OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
Junzhe Chen, Tianshu Zhang, Shiyu Huang +6
Recently, Omni-modal large language models (OLLMs) have sparked a new wave of research, achieving impressive results in tasks such as audio-video understanding and real-time enviro…
ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
Junzhe Chen, Tianshu Zhang, Shiyu Huang +4
Despite the recent breakthroughs achieved by Large Vision Language Models (LVLMs) in understanding and responding to complex visual-textual contexts, their inherent hallucination t…
On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations
Shiao Meng, Xuming Hu, Aiwei Liu +4
Driven by the demand for cross-sentence and large-scale relation extraction, document-level relation extraction (DocRE) has attracted increasing research interest. Despite the cont…
MarkLLM: An Open-Source Toolkit for LLM Watermarking
Leyi Pan, Aiwei Liu, Zhiwei He +9
LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential…
FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues
Shuang Li, Jiahua Wang, Lijie Wen
Multi-modal reasoning plays a vital role in bridging the gap between textual and visual information, enabling a deeper understanding of the context. This paper presents the Feature…
LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments
Junzhe Chen, Xuming Hu, Shuodi Liu +4
Recent advancements in large language models (LLMs) have revealed their potential for achieving autonomous agents possessing human-level intelligence. However, existing benchmarks…
Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions
Xuming Hu, Xiaochuan Li, Junzhe Chen +8
Generative search engines have the potential to transform how people seek information online, but generated responses from existing large language models (LLMs)-backed generative s…
A Survey of Text Watermarking in the Era of Large Language Models
Aiwei Liu, Leyi Pan, Yijian Lu +7
Text watermarking algorithms are crucial for protecting the copyright of textual content. Historically, their capabilities and application scenarios were limited. However, recent a…
Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction
Xuming Hu, Junzhe Chen, Aiwei Liu +3
How can we better extract entities and relations from text? Using multimodal extraction with images and text obtains more signals for entities and relations, and aligns them throug…
RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction
Shiao Meng, Xuming Hu, Aiwei Liu +4
How to identify semantic relations among entities in a document when only a few labeled documents are available? Few-shot document-level relation extraction (FSDLRE) is crucial for…
Do Large Language Models Know about Facts?
Xuming Hu, Junzhe Chen, Xiaochuan Li +4
Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks. The factual knowledge acquired during pretr…
A Semantic Invariant Robust Watermark for Large Language Models
Aiwei Liu, Leyi Pan, Xuming Hu +2
Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra wate…
An Unforgeable Publicly Verifiable Watermark for Large Language Models
Aiwei Liu, Leyi Pan, Xuming Hu +4
Recently, text watermarking algorithms for large language models (LLMs) have been proposed to mitigate the potential harms of text generated by LLMs, including fake news and copyri…
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing
Aiwei Liu, Wei Liu, Xuming Hu +4
In the context-dependent Text-to-SQL task, the generated SQL statements are refined iteratively based on the user input utterance from each interaction. The input text from each in…
Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer
Shuang Li, Xuming Hu, Aiwei Liu +4
Cross-lingual natural language inference is a fundamental problem in cross-lingual language understanding. Many recent works have used prompt learning to address the lack of annota…
Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition
Yawen Yang, Xuming Hu, Fukun Ma +4
Named Entity Recognition (NER) is a well and widely studied task in natural language processing. Recently, the nested NER has attracted more attention since its practicality and di…
Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence
Xuming Hu, Zhaochen Hong, Zhijiang Guo +2
Real-world fact verification task aims to verify the factuality of a claim by retrieving evidence from the source document. The quality of the retrieved evidence plays an important…
Give Me More Details: Improving Fact-Checking with Latent Retrieval
Xuming Hu, Junzhe Chen, Zhijiang Guo +1
Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the…
A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability
Aiwei Liu, Xuming Hu, Lijie Wen +1
This paper presents the first comprehensive analysis of ChatGPT's Text-to-SQL ability. Given the recent emergence of large-scale conversational language model ChatGPT and its impre…
Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction
Xuming Hu, Shiao Meng, Chenwei Zhang +4
Information Extraction (IE) aims to extract structured information from heterogeneous sources. IE from natural language texts include sub-tasks such as Named Entity Recognition (NE…
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution
Aiwei Liu, Honghai Yu, Xuming Hu +5
We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split int…
Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks
Xuming Hu, Yong Jiang, Aiwei Liu +5
Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks). Existing augmentation…
Scene Graph Modification as Incremental Structure Expanding
Xuming Hu, Zhijiang Guo, Yu Fu +2
A scene graph is a semantic representation that expresses the objects, attributes, and relationships between objects in a scene. Scene graphs play an important role in many cross m…
Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph
Aiwei Liu, Xuming Hu, Li Lin +1
The generalizability to new databases is of vital importance to Text-to-SQL systems which aim to parse human utterances into SQL statements. Existing works achieve this goal by lev…