Search Results for author: Yujia Zhou

Found 32 papers, 19 papers with code

RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects

1 code implementation30 Jan 2025 Yiteng Tu, Weihang Su, Yujia Zhou, Yiqun Liu, Qingyao Ai

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base.

counterfactual RAG +1

Parametric Retrieval Augmented Generation

1 code implementation27 Jan 2025 Weihang Su, Yichen Tang, Qingyao Ai, Junxi Yan, Changyue Wang, Hongning Wang, Ziyi Ye, Yujia Zhou, Yiqun Liu

To this end, we introduce Parametric retrieval-augmented generation (Parametric RAG), a new RAG paradigm that integrates external knowledge directly into the parameters of feed-forward networks (FFN) of an LLM through document parameterization.

Domain Adaptation RAG +1

Search-o1: Agentic Search-Enhanced Large Reasoning Models

1 code implementation9 Jan 2025 Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, Zhicheng Dou

To address this limitation, we introduce \textbf{Search-o1}, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents.

Code Generation +4

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

1 code implementation16 Dec 2024 Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Qi Ye, Zhicheng Dou

Moreover, to mitigate false pruning in the process of constrained evidence generation, we introduce (1) hierarchical FM-Index constraints, which generate corpus-constrained clues to identify a subset of relevant documents before evidence generation, reducing irrelevant decoding space; and (2) a forward-looking constrained decoding strategy, which considers the relevance of future sequences to improve evidence accuracy.

RAG Retrieval

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

1 code implementation7 Dec 2024 Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, Yiqun Liu

Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions.

AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant

1 code implementation11 Nov 2024 Yujia Zhou, Zheng Liu, Zhicheng Dou

The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination".

Decision Making Hallucination +3

CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges

1 code implementation20 Oct 2024 Haitao Li, Junjie Chen, Qingyao Ai, Zhumin Chu, Yujia Zhou, Qian Dong, Yiqun Liu

The use of large language models (LLMs) as automated evaluation tools to assess the quality of generated natural language, known as LLMs-as-Judges, has demonstrated promising capabilities and is rapidly gaining widespread attention.

Fairness Prediction +1

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data

no code implementations1 Oct 2024 Ziyi Ye, Xiangsheng Li, Qiuchi Li, Qingyao Ai, Yujia Zhou, Wei Shen, Dong Yan, Yiqun Liu

Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to produce a scalar score as preference or reward.

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

1 code implementation16 Sep 2024 Yujia Zhou, Yan Liu, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Zheng Liu, Chaozhuo Li, Zhicheng Dou, Tsung-Yi Ho, Philip S. Yu

Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs).

Fairness Hallucination +3

Are Long-LLMs A Necessity For Long-Context Tasks?

no code implementations24 May 2024 Hongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao, Yujia Zhou, Xu Chen, Zhicheng Dou

The learning and deployment of long-LLMs remains a challenging problem despite recent progresses.

From Matching to Generation: A Survey on Generative Information Retrieval

1 code implementation23 Apr 2024 Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yuyao Zhang, Peitian Zhang, Yutao Zhu, Zhicheng Dou

We will summarize the advancements in GR regarding model training, document identifier, incremental learning, downstream tasks adaptation, multi-modal GR and generative recommendation, as well as progress in reliable response generation in aspects of internal knowledge memorization, external knowledge augmentation, generating response with citations and personal information assistant.

Incremental Learning Information Retrieval +6

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models

2 code implementations11 Mar 2024 Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, Yiqun Liu

Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate.

Hallucination

BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence

no code implementations19 Feb 2024 Jiajie Jin, Yutao Zhu, Yujia Zhou, Zhicheng Dou

Retrieval-augmented large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, addressing inherent challenges in knowledge update and factual inadequacy.

Question Answering Retrieval

Metacognitive Retrieval-Augmented Large Language Models

1 code implementation18 Feb 2024 Yujia Zhou, Zheng Liu, Jiajie Jin, Jian-Yun Nie, Zhicheng Dou

Drawing from cognitive psychology, metacognition allows an entity to self-reflect and critically evaluate its cognitive processes.

Response Generation Retrieval

Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism

no code implementations16 Feb 2024 Yujia Zhou, Qiannan Zhu, Jiajie Jin, Zhicheng Dou

To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query logs.

Grounding Language Model with Chunking-Free In-Context Retrieval

no code implementations15 Feb 2024 Hongjin Qian, Zheng Liu, Kelong Mao, Yujia Zhou, Zhicheng Dou

These strategies not only improve the efficiency of the retrieval process but also ensure that the fidelity of the generated grounding text evidence is maintained.

Chunking Language Modeling +4

CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks

no code implementations2 Feb 2024 Xiaoxi Li, Zhicheng Dou, Yujia Zhou, Fangchao Liu

We design the following mechanisms to facilitate effective retrieval and generation, and improve the end-to-end effectiveness of KI tasks: (1) We develop a ranking-oriented DocID list generation strategy, which refines GR by directly learning from a DocID ranking list, to improve retrieval quality.

Answer Generation Hallucination +4

UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models

no code implementations18 Dec 2023 Xiaoxi Li, Yujia Zhou, Zhicheng Dou

Generative information retrieval, encompassing two major tasks of Generative Document Retrieval (GDR) and Grounded Answer Generation (GAR), has gained significant attention in the area of information retrieval and natural language processing.

Answer Generation Information Retrieval +2

Generative Retrieval via Term Set Generation

1 code implementation23 May 2023 Peitian Zhang, Zheng Liu, Yujia Zhou, Zhicheng Dou, Fangchao Liu, Zhao Cao

On top of the term-set DocID, we propose a permutation-invariant decoding algorithm, with which the term set can be generated in any permutation yet will always lead to the corresponding document.

Information Retrieval Natural Questions +1

Ultron: An Ultimate Retriever on Corpus with a Model-based Indexer

no code implementations19 Aug 2022 Yujia Zhou, Jing Yao, Zhicheng Dou, Ledell Wu, Peitian Zhang, Ji-Rong Wen

In order to unify these two stages, we explore a model-based indexer for document retrieval.

Retrieval

Socialformer: Social Network Inspired Long Document Modeling for Document Ranking

1 code implementation22 Feb 2022 Yujia Zhou, Zhicheng Dou, Huaying Yuan, Zhengyi Ma

In this paper, we propose the model Socialformer, which introduces the characteristics of social networks into designing sparse attention patterns for long document modeling in document ranking.

Document Ranking

PSSL: Self-supervised Learning for Personalized Search with Contrastive Sampling

1 code implementation24 Nov 2021 Yujia Zhou, Zhicheng Dou, Yutao Zhu, Ji-Rong Wen

Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors.

Self-Supervised Learning Sentence

Group based Personalized Search by Integrating Search Behaviour and Friend Network

1 code implementation24 Nov 2021 Yujia Zhou, Zhicheng Dou, Bingzheng Wei, Ruobing Xievand Ji-Rong Wen

Specifically, we propose a friend network enhanced personalized search model, which groups the user into multiple friend circles based on search behaviours and friend relations respectively.

Re-Ranking

Simple Recurrent Neural Networks is all we need for clinical events predictions using EHR data

1 code implementation3 Oct 2021 Laila Rasmy, Jie Zhu, Zhiheng Li, Xin Hao, Hong Thoai Tran, Yujia Zhou, Firat Tiryaki, Yang Xiang, Hua Xu, Degui Zhi

As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models.

Bayesian Optimization

Numerical Simulation of Bubbly Flow Using Partially Averaged Navier−Stokes Simulation and a Path Oscillation Model in the Euler−Lagrange Approach

no code implementations journal 2021 Yujia Zhou, Chenru Zhao, Bingqiang Ji, and Hanliang Bo

Large bubbles always undergo asymmetric paths due to the wake instability, which was rarely considered in the simulation of bubbly flow in complex flow systems such as bubble columns.

COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model

no code implementations13 Jul 2020 Jingqi Wang, Noor Abu-el-rub, Josh Gray, Huy Anh Pham, Yujia Zhou, Frank Manion, Mei Liu, Xing Song, Hua Xu, Masoud Rouhizadeh, Yaoyun Zhang

To this end, this study aims at adapting the existing CLAMP natural language processing tool to quickly build COVID-19 SignSym, which can extract COVID-19 signs/symptoms and their 8 attributes (body location, severity, temporal expression, subject, condition, uncertainty, negation, and course) from clinical text.

Negation

Cannot find the paper you are looking for? You can Submit a new open access paper.