14 citations · 26 across the 25 of their papers we have counts for
18 papers · 1 filter
CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge Conflicts
Xuhua Ma, Richong Zhang, Zhijie Nie
Retrieval-Augmented Generation (RAG) often struggles with knowledge conflicts, where model-internal parametric knowledge overrides retrieved evidence, leading to unfaithful outputs…
AR-BENCH: Benchmarking Legal Reasoning with Judgment Error Detection, Classification and Correction
Yifei Li, Richong Zhang, Wanyu Tu +4
Legal judgments may contain errors due to the complexity of case circumstances and the abstract nature of legal concepts, while existing appellate review mechanisms face efficiency…
inversedMixup: Data Augmentation via Inverting Mixed Embeddings
Fanshuang Kong, Richong Zhang, Qiyu Sun +3
Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates at the latent embedding level, the resulting sam…
Text2Token: Unsupervised Text Representation Learning with Token Target Prediction
Ruize An, Richong Zhang, Zhijie Nie +3
Unsupervised text representation learning (TRL) is a fundamental task in natural language processing, which is beneficial for improving search and recommendations with the web's un…
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
Ziyang Miao, Qiyu Sun, Jingyuan Wang +4
Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quali…
Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning
Pieyi Zhang, Richong Zhang, Zhijie Nie
Multi-task prompt tuning utilizes multiple high-resource source tasks to improve performance on low-source target tasks. Existing approaches transfer the soft prompt trained by com…
A Graph-based Verification Framework for Fact-Checking
Yani Huang, Richong Zhang, Zhijie Nie +2
Fact-checking plays a crucial role in combating misinformation. Existing methods using large language models (LLMs) for claim decomposition face two key limitations: (1) insufficie…
Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation
Junhao Zhang, Richong Zhang, Fanshuang Kong +3
Existing long-text generation methods produce lengthy outputs from short inputs, leaving long-input-to-long-output generation underexplored. As input length increases, LLMs increas…
General Table Question Answering via Answer-Formula Joint Generation
Zhongyuan Wang, Richong Zhang, Zhijie Nie +1
Advanced table question answering (TableQA) methods prompt large language models (LLMs) to generate answer text, SQL query, Python code, or custom operation, which impressively imp…
LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning
Fanshuang Kong, Richong Zhang, Ziqiao Wang
Hierarchical text classification (HTC) aims to assign one or more labels in the hierarchy for each text. Many methods represent this structure as a global hierarchy, leading to red…
When Text Embedding Meets Large Language Model: A Comprehensive Survey
Zhijie Nie, Zhangchi Feng, Mingxin Li +4
Text embedding has become a foundational technology in natural language processing (NLP) during the deep learning era, driving advancements across a wide array of downstream tasks.…
Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging
Mingxin Li, Zhijie Nie, Yanzhao Zhang +3
Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks…
EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
Zhangchi Feng, Dongdong Kuang, Zhongyuan Wang +3
This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The…
Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios
Zhongyuan Wang, Richong Zhang, Zhijie Nie +1
Recent Text-to-SQL methods leverage large language models (LLMs) by incorporating feedback from the database management system. While these methods effectively address execution er…
Activated Parameter Locating via Causal Intervention for Model Merging
Fanshuang Kong, Richong Zhang, Ziqiao Wang
Model merging combines multiple homologous models into one model, achieving convincing generalization without the necessity of additional training. A key challenge in this problem…
A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens
Zhijie Nie, Richong Zhang, Zhanyu Wu
Text embeddings from large language models (LLMs) have achieved excellent results in tasks such as information retrieval, semantic textual similarity, etc. In this work, we show an…
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
Yaowei Zheng, Richong Zhang, Junhao Zhang +4
Efficient fine-tuning is vital for adapting large language models (LLMs) to downstream tasks. However, it requires non-trivial efforts to implement these methods on different model…
Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient
Mingxin Li, Richong Zhang, Zhijie Nie
Sentence Representation Learning (SRL) is a crucial task in Natural Language Processing (NLP), where contrastive Self-Supervised Learning (SSL) is currently a mainstream approach.…