14 citations · 26 across the 25 of their papers we have counts for
27 papers
DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval
Jingyuan Wang, Richong Zhang, Zhijie Nie +2
Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing…
ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation
Yiru Dong, Richong Zhang, Fanshuang Kong +1
Large language models (LLMs) have made notable progress in code generation, but they still struggle on challenging tasks that require sophisticated algorithms or complex implementa…
Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
Maham Nazir, Muhammad Aqeel, Richong Zhang +1
Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classificat…
Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation
Yaowei Zheng, Richong Zhang, Shenxi Wu +5
We study finite-horizon continuous-time policy evaluation from discrete closed-loop trajectories under time-inhomogeneous dynamics. The target value surface solves a backward parab…
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…
Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
Zhanyu Wu, Richong Zhang, Zhijie Nie
Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a…
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…
MOMA: Masked Orthogonal Matrix Alignment for Zero-Additional-Parameter Model Merging
Fanshuang Kong, Richong Zhang, Zhijie Nie +4
Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric mis…
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.…
MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective
Hailang Huang, Yong Wang, Zixuan Huang +4
Large Multimodal Models (LMMs) demonstrate impressive capabilities. However, current benchmarks predominantly focus on image comprehension in specific domains, and these benchmarks…
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…
Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning
Zhijie Nie, Richong Zhang, Zhangchi Feng +2
Cross-lingual Cross-modal Retrieval (CCR) is an essential task in web search, which aims to break the barriers between modality and language simultaneously and achieves image-text…
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…