大模型相关文章
大模型相关文章
- 论文列表
- 1.查询重写器
- 1.1提示方法
- 1.2微调方法
- 1.3知识蒸馏方法
- 2.检索器
- 2.1利用LLMs生成搜索数据
- 2.2利用LLMs增强模型架构
- 3.重排器
- 3.1利用LLMs作为监督重排器
- 3.2利用LLMs作为无监督重排器
- 3.3利用LLMs进行训练数据增强
- 4.阅读器
- 4.1被动阅读器
- 4.2主动阅读器
- 4.3压缩器
- 4.4分析
- 4.5应用
- 5.搜索代理
- 5.1静态代理
- 5.2动态代理
- 6.其他资源
来源：LLM4IR-Survey
论文列表
1.查询重写器
1.1提示方法
- Query2doc: Query Expansion with Large Language Models, Wang et al., arXiv 2023. [Paper]
利用大型语言模型进行查询扩展。 - Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval, Mackie et al., arXiv 2023. [Paper]
针对稀疏、密集和学习到的稀疏检索的生成式和伪相关反馈。 - Generative Relevance Feedback with Large Language Models, Mackie et al., SIGIR 2023 (short paper). [Paper]
利用大型语言模型进行生成式相关性反馈。 - GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval, Mackie et al., arXiv 2023. [Paper]
GRM：使用相关性感知样本估计的生成式相关性建模，用于文档检索。 - Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search, Mao et al., arXiv 2023. [Paper]
大型语言模型了解您的上下文搜索意图：面向对话搜索的提示框架。 - Precise Zero-Shot Dense Retrieval without Relevance Labels, Gao et al., ACL 2023. [Paper]
无需相关性标签的精确零样本密集检索。 - Query Expansion by Prompting Large Language Models, Jagerman et al., arXiv 2023. [Paper]
通过提示大型语言模型进行查询扩展。 - Large Language Models are Strong Zero-Shot Retriever, Shen et al., arXiv 2023. [Paper]
大型语言模型是强大的零样本检索器。 - Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting, Ye et al., EMNLP 2023 (Findings). [Paper]
增强对话搜索：大型语言模型辅助的信息查询重写。 - Can generative llms create query variants for test collections? an exploratory study, M. Alaofi et al., SIGIR 2023 (short paper). [Paper]
生成式大型语言模型能否为测试集创建查询变体？一项探索性研究。 - Corpus-Steered Query Expansion with Large Language Models, Lei et al., EACL 2024 (Short Paper). [Paper]
基于语料库引导的大型语言模型查询扩展。 - Large language model based long-tail query rewriting in taobao search, Peng et al., WWW 2024. [Paper]
基于大型语言模型的淘宝搜索长尾查询重写。 - Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?, Li et al., SIGIR 2024. [Paper]
查询扩展能否提高强交叉编码器排序器的泛化能力？ - Query Performance Prediction using Relevance Judgments Generated by Large Language Models, Meng et al., arXiv 2024. [Paper]
利用大型语言模型生成的相关性判断进行查询性能预测 - RaFe: Ranking Feedback Improves Query Rewriting for RAG, Mao et al., arXiv 2024. [Paper]
RaFe：排序反馈改进了RAG的查询重写 - Crafting the Path: Robust Query Rewriting for Information Retrieval, Baek et al., arXiv 2024. [Paper]
打造路径：信息检索中的稳健查询重写 - Query Rewriting for Retrieval-Augmented Large Language Models, Ma et al., arXiv 2023. [Paper]
检索增强型大型语言模型的查询重写
1.2微调方法
- QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation, Srinivasan et al., EMNLP 2022 (Industry). [Paper] (This paper explore fine-tuning methods in baseline experiments.)
利用检索增强和多阶段蒸馏的大型语言模型查询意图
1.3知识蒸馏方法
- QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation, Srinivasan et al., EMNLP 2022 (Industry). [Paper]
利用检索增强和多阶段蒸馏的大型语言模型查询意图 - Knowledge Refinement via Interaction Between Search Engines and Large Language Models, Feng et al., arXiv 2023. [Paper]
通过搜索引擎与大型语言模型之间的交互进行知识精炼。 - Query Rewriting for Retrieval-Augmented Large Language Models, Ma et al., arXiv 2023. [Paper]
面向检索增强的大型语言模型查询重写
2.检索器
2.1利用LLMs生成搜索数据
- InPars: Data Augmentation for Information Retrieval using Large Language Models, Bonifacio et al., arXiv 2022. [Paper]
InPars: 使用大型语言模型进行信息检索的数据增强 - Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval, Ma et al., arXiv 2023. [Paper]
基于大型语言模型文档扩展的密集段落检索预训练 - InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval, Jeronymo et al., arXiv 2023. [Paper]
InPars-v2: 大型语言模型作为信息检索的高效数据集生成器 - Promptagator: Few-shot Dense Retrieval From 8 Examples, Dai et al., ICLR 2023. [Paper]
Promptagator: 从8个示例中进行少样本密集检索 - AugTriever: Unsupervised Dense Retrieval by Scalable Data Augmentation, Meng et al., arXiv 2023. [Paper]
AugTriever: 通过可扩展数据增强进行无监督密集检索 - UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers, Saad-Falco et al., arXiv 2023. [Paper]
UDAPDR: 通过LLM提示和重排器蒸馏进行无监督领域适应 - Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models, Peng et al., arXiv 2023. [Paper]
软提示调优以增强大型语言模型的密集检索 - CONVERSER: Few-shot Conversational Dense Retrieval with Synthetic Data Generation, Huang et al., ACL 2023. [Paper]
CONVERSER: 使用合成数据生成进行少样本对话密集检索 - Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval, Thakur et al., arXiv 2023. [Paper]
利用LLMs为多语言密集检索合成多语言训练数据 - Questions Are All You Need to Train a Dense Passage Retriever, Sachan et al., ACL 2023. [Paper]
问题是你训练密集段落检索器所需的一切 - Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators, Chen et al., EMNLP 2023. [Paper]
超越事实性: 大型语言模型作为知识生成器的全面评估 - Gecko: Versatile Text Embeddings Distilled from Large Language Models, Lee et al., arXiv 2024. [Paper]
Gecko: 从大型语言模型中提取的多功能文本嵌入 - Improving Text Embeddings with Large Language Models, Wang et al., ACL 2024. [Paper]
使用大型语言模型改进文本嵌入
2.2利用LLMs增强模型架构
- Text and Code Embeddings by Contrastive Pre-Training, Neelakantan et al., arXiv 2022. [Paper]
通过对比预训练生成文本和代码嵌入 - Fine-Tuning LLaMA for Multi-Stage Text Retrieval, Ma et al., arXiv 2023. [Paper]
微调LLaMA进行多阶段文本检索 - Large Dual Encoders Are Generalizable Retrievers, Ni et al., EMNLP 2022. [Paper]
大型双编码器是可泛化的检索器 - Task-aware Retrieval with Instructions, Asai et al., ACL 2023 (Findings). [Paper]
任务感知检索与指令 - Transformer memory as a differentiable search index, Tay et al., NeurIPS 2022. [Paper]
Transformer记忆作为可微分搜索索引 - Large Language Models are Built-in Autoregressive Search Engines, Ziems et al., ACL 2023 (Findings). [Paper]
大型语言模型是内置的自回归搜索引擎 - Chatretriever: Adapting large language models for generalized and robust conversational dense retrieval, Mao et al., arXiv. [Paper]
Chatretriever: 适应大型语言模型进行通用且鲁棒的对话密集检索 - How does generative retrieval scale to millions of passages?, Pradeep et al., ACL 2023. [Paper]
生成式检索如何扩展到数百万段落?, Pradeep et al - CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks, Li et al., SIGIR. [Paper]
CorpusLM: 面向知识密集型任务的统一语言模型
3.重排器
3.1利用LLMs作为监督重排器
- Multi-Stage Document Ranking with BERT, Nogueira et al., arXiv 2019. [Paper]
使用BERT进行多阶段文档排序 - Document Ranking with a Pretrained Sequence-to-Sequence Model, Nogueira et al., EMNLP 2020 (Findings). [Paper]
使用预训练序列到序列模型进行文档排序 - Text-to-Text Multi-view Learning for Passage Re-ranking, Ju et al., SIGIR 2021 (Short Paper). [Paper]
用于段落重排的多视图学习文本到文本模型 - The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models, Pradeep et al., arXiv 2021. [Paper]
Expando-Mono-Duo设计模式: 使用预训练序列到序列模型进行文本排序 - RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses, Zhuang et al., SIGIR 2023 (Short Paper). [Paper]
RankT5: 使用排序损失微调T5进行文本排序 - Fine-Tuning LLaMA for Multi-Stage Text Retrieval, Ma et al., arXiv 2023. [Paper]
微调LLaMA进行多阶段文本检索 - A Two-Stage Adaptation of Large Language Models for Text Ranking, Zhang et al., ACL 2024 (Findings). [Paper]
大型语言模型在文本排序中的两阶段适应 - Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models, Zhang et al., arXiv 2023. [Paper]
Rank-without-GPT: 基于开源大型语言模型构建独立于GPT的列表式重排器 - ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval, Yoon et al., ACL 2024. [Paper]
ListT5: 使用融合解码器进行列表式重排以改进零样本检索 - Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models, Peng et al., arXiv 2024. [Paper]
Q-PEFT: 基于查询的参数高效微调用于大型语言模型的文本重排 - Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models, Liu et al., arXiv 2024. [Paper]
利用段落嵌入进行高效列表式重排与大型语言模型
3.2利用LLMs作为无监督重排器
- Holistic Evaluation of Language Models, Liang et al., arXiv 2022. [Paper]
语言模型的整体评估 - Improving Passage Retrieval with Zero-Shot Question Generation, Sachan et al., EMNLP 2022. [Paper]
通过零样本问题生成改进段落检索 - Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker, Cho et al., ACL 2023 (Findings). [Paper]
通过约束生成进行离散提示优化以实现零样本重排 - Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking, Zhuang et al., EMNLP 2023 (Findings). [Paper]
开源大型语言模型是文档排序的强零样本查询似然模型 - PaRaDe: Passage Ranking using Demonstrations with Large Language Models, Drozdov et al., EMNLP 2023 (Findings). [Paper]
PaRaDe: 使用大型语言模型进行段落排序的演示 - Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels, Zhuang et al., arXiv 2023. [Paper]
超越是与否: 通过细粒度相关性标签评分改进零样本LLM排序器 - Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent, Sun et al., EMNLP 2023. [Paper]
ChatGPT在搜索中表现如何? 探究大型语言模型作为重排代理 - Zero-Shot Listwise Document Reranking with a Large Language Model, Ma et al., arXiv 2023. [Paper]
零样本列表式文档重排与大型语言模型 - Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models, Tang et al., arXiv 2023. [Paper]
中间发现: 排列自一致性改进大型语言模型中的列表式排序 - Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting, Qin et al., NAACL 2024 (Findings). [Paper]
大型语言模型通过成对排序提示进行有效文本排序 - A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models, Zhuang et al., SIGIR 2024. [Paper]
一种集合方法用于有效且高效的零样本排序与大型语言模型 - InstUPR: Instruction-based Unsupervised Passage Reranking with Large Language Models, Huang and Chen, arXiv 2024. [Paper]
InstUPR: 基于指令的无监督段落重排与大型语言模型 - Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers, Guo et al., arXiv 2024. [Paper]
即时生成多样化标准以改进点式LLM排序器 - DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Task, Liu et al., arXiv 2024. [Paper]
DemoRank: 在排序任务中为大型语言模型选择有效演示 - An Investigation of Prompt Variations for Zero-shot LLM-based Rankers, Sun et al., arXiv 2024. [Paper]
零样本LLM排序器的提示变体研究 - TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy, Chen et al., arXiv 2024. [Paper]
TourRank: 利用大型语言模型通过锦标赛启发策略进行文档排序 - Top-Down Partitioning for Efficient List-Wise Ranking, Parry et al., arXiv 2024. [Paper]
自顶向下分区以实现高效列表式排序 - PRP-Graph: Pairwise Ranking Prompting to LLMs with Graph Aggregation for Effective Text Re-ranking, Luo et al., ACL 2024. [Paper]
PRP-Graph: 通过图聚合进行成对排序提示以实现有效文本重排 - Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing, Yan et al., arXiv 2024. [Paper]
通过后处理整合大型语言模型的排序和相关性预测
3.3利用LLMs进行训练数据增强
- ExaRanker: Explanation-Augmented Neural Ranker, Ferraretto et al., SIGIR 2023 (Short Paper). [Paper]
ExaRanker: 解释增强型神经排序器 - InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers, Boytsov et al., arXiv 2023. [Paper]
InPars-Light: 高效排序器的成本效益无监督训练 - Generating Synthetic Documents for Cross-Encoder Re-Rankers, Askari et al., arXiv 2023. [Paper]
生成合成文档用于跨编码器重排序器 - Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers, Sun et al., arXiv 2023. [Paper]
指令蒸馏使大型语言模型成为高效的零样本排序器 - RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models, Pradeep et al., arXiv 2023. [Paper]
RankVicuna: 使用开源大型语言模型进行零样本列表式文档重排序 - RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!, Pradeep et al., arXiv 2023. [Paper]
RankZephyr: 有效且稳健的零样本列表式重排序轻而易举！ - ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs, Ferraretto et al., arXiv 2024. [Paper]
ExaRanker-Open: 使用开源 LLM 为信息检索生成合成解释 - Expand, Highlight, Generate: RL-driven Document Generation for Passage Reranking, Askari et al., EMNLP 2023. [Paper]
扩展、突出、生成：RL 驱动的文档生成用于段落重排序 - FIRST: Faster Improved Listwise Reranking with Single Token Decoding, Reddy et al., arXiv 2024. [Paper]
FIRST: 使用单令牌解码的更快改进列表式重排序
4.阅读器
4.1被动阅读器
- REALM: Retrieval-Augmented Language Model Pre-Training, Guu et al., ICML 2020. [Paper]
REALM: 检索增强型语言模型预训练 - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, Lewis et al., NeurIPS 2020. [Paper]
知识密集型 NLP 任务的检索增强生成 - REPLUG: Retrieval-Augmented Black-Box Language Models, Shi et al., arXiv 2023. [Paper]
REPLUG: 检索增强型黑箱语言模型 - Atlas: Few-shot Learning with Retrieval Augmented Language Models, Izacard et al., JMLR 2023. [Paper]
Atlas: 使用检索增强型语言模型进行少样本学习 - Internet-augmented Language Models through Few-shot Prompting for Open-domain Question Answering, Lazaridou et al., arXiv 2022. [Paper]
通过少样本提示增强互联网的语言模型用于开放域问答 - Rethinking with Retrieval: Faithful Large Language Model Inference, He et al., arXiv 2023. [Paper]
通过检索重新思考：忠实的大型语言模型推理 - FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation, Vu et al., arxiv 2023. [Paper]
FreshLLMs: 通过搜索引擎增强刷新大型语言模型 - Enabling Large Language Models to Generate Text with Citations, Gao et al., EMNLP 2023. [Paper]
使大型语言模型生成带有引用的文本 - Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models, Yu et al., arxiv 2023. [Paper]
Chain-of-Note: 增强检索增强型语言模型的鲁棒性 - Improving Retrieval-Augmented Large Language Models via Data Importance Learning, Lyu et al., arXiv 2023. [Paper]
通过数据重要性学习改进检索增强型大型语言模型 - Search Augmented Instruction Learning, Luo et al., EMNLP 2023 (Findings). [Paper]
搜索增强指令学习 - RADIT: Retrieval-Augmented Dual Instruction Tuning, Lin et al., arXiv 2023. [Paper]
RADIT: 检索增强型双重指令微调 - Improving Language Models by Retrieving from Trillions of Tokens, Borgeaud et al., ICML 2022. [Paper]
通过从万亿个标记中检索改进语言模型 - In-Context Retrieval-Augmented Language Models, Ram et al., arXiv 2023. [Paper]
上下文检索增强型语言模型 - Interleaving Retrieval with Chain-of-thought Reasoning for Knowledge-intensive Multi-step Questions, Trivedi et al., ACL 2023. [Paper]
通过链式思维推理与检索交织解决知识密集型多步骤问题 - Improving Language Models via Plug-and-Play Retrieval Feedback, Yu et al., arXiv 2023. [Paper]
通过即插即用检索反馈改进语言模型 - Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy, Shao et al., EMNLP 2023 (Findings). [Paper]
通过迭代检索-生成协同增强检索增强型大型语言模型 - Retrieval-Generation Synergy Augmented Large Language Models, Feng et al., arXiv 2023. [Paper]
检索-生成协同增强大型语言模型 - Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection, Asai et al., arXiv 2023. [Paper]
Self-RAG: 通过自我反思学习检索、生成和批判 - Active Retrieval Augmented Generation, Jiang et al., EMNLP 2023. [Paper]
主动检索增强生成
4.2主动阅读器
- Measuring and Narrowing the Compositionality Gap in Language Models, Press et al., arXiv 2022. [Paper]
测量并缩小语言模型中的组合性差距 - DEMONSTRATE–SEARCH–PREDICT: Composing Retrieval and Language Models for Knowledge-intensive NLP, Khattab et al., arXiv 2022. [Paper]
DEMONSTRATE–SEARCH–PREDICT: 组合检索和语言模型用于知识密集型 NLP - Answering Questions by Meta-Reasoning over Multiple Chains of Thought, Yoran et al., arXiv 2023. [Paper]
通过元推理多条思维链回答问题 - PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers, Lee ei al., arXiv 2024. [Paper]
PlanRAG: 计划-检索增强生成用于生成大型语言模型作为决策者 - Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs, Wang et al., arXiv 2024. [Paper]
从知识图谱中学习检索增强型大型语言模型的规划
4.3压缩器
- LeanContext: Cost-Efficient Domain-Specific Question Answering Using LLMs, Arefeen et al., arXiv 2023. [Paper]
LeanContext: 使用 LLM 进行成本效益的特定领域问答 - RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation, Xu et al., arXiv 2023. [Paper]
RECOMP: 通过压缩和选择性增强改进检索增强型 LMs - TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction, Liu et al., EMNLP 2023 (Findings). [Paper]
TCRA-LLM: 令牌压缩检索增强型大型语言模型用于推理成本降低 - Learning to Filter Context for Retrieval-Augmented Generation, Wang et al., arXiv 2023. [Paper]
学习过滤上下文用于检索增强型生成
4.4分析
- Lost in the Middle: How Language Models Use Long Contexts, Liu et al., arXiv 2023. [Paper]
迷失：语言模型如何使用长上下文 - Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation, Ren et al., arXiv 2023. [Paper]
通过检索增强调查大型语言模型的事实知识边界 - Exploring the Integration Strategies of Retriever and Large Language Models, Liu et al., arXiv 2023. [Paper]
探索检索器和大型语言模型的集成策略 - Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models, Aksitov et al., arXiv 2023. [Paper]
检索增强型大型语言模型的归因和流畅性权衡特征 - When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories, Mallen et al., ACL 2023. [Paper]
何时不信任语言模型：调查参数和非参数记忆的有效性
4.5应用
- Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering, Wang et al., arXiv 2023. [Paper]
通过医学教科书增强黑箱 LLM 用于临床问答 - ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science, Munikoti et al., arXiv 2023. [Paper]
ATLANTIC: 结构感知检索增强型语言模型用于跨学科科学 - Crosslingual Retrieval Augmented In-context Learning for Bangla, Li et al., arXiv 2023. [Paper]
跨语言检索增强型上下文学习用于孟加拉语 - Clinfo.ai: An Open-Source Retrieval-Augmented Large Language Model System for Answering Medical Questions using Scientific Literature, Lozano et al., arXiv 2023. [Paper]
Clinfo.ai: 一个开源检索增强型大型语言模型系统，使用科学文献回答医学问题 - Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models, Zhang et al., ICAIF 2023. [Paper]
通过检索增强型大型语言模型增强金融情感分析 - Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models, Louis et al., arXiv 2023. [Paper]
通过检索增强型大型语言模型进行可解释的长篇法律问答 - RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit, Liu et al., arXiv 2023. [Paper]
RETA-LLM: 一个检索增强型大型语言模型工具包 - Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models, Jiang et al., arXiv 2023. [Paper]
Chameleon: 一个用于检索增强型语言模型的异构和解耦加速器系统 - RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models, Hoshi et al., EMNLP 2023. [Paper]
RaLLe: 一个开发和评估检索增强型大型语言模型的框架 - Don’t forget private retrieval: distributed private similarity search for large language models, Zyskind et al., arXiv 2023. [Paper]
不要忘记私有检索：分布式私有相似性搜索用于大型语言模型
5.搜索代理
5.1静态代理
- LaMDA: Language Models for Dialog Applications, Thoppilan et al., arXiv 2022. [Paper]
LaMDA: 对话应用的语言模型 - Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion, Shuster et al., EMNLP 2022 (Findings). [Paper]
寻求知识的语言模型：对话和提示完成的模块化搜索与生成 - Teaching language models to support answers with verified quotes, Menick et al., arXiv 2022. [Paper]
教授语言模型用已验证的引文支持答案 - WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences, Liu et al., KDD 2023. [Paper]
WebGLM: 基于人类偏好的高效网页增强问答系统 - A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis, Gur et al., arXiv 2023. [Paper]
一个具有规划、长上下文理解和程序合成的真实世界WebAgent - Know Where to Go: Make LLM a Relevant, Responsible, and Trustworthy Searcher, Shi et al., arXiv 2023. [Paper]
让LLM成为相关、负责且值得信赖的搜索者 - CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models, Gong et al., SIGIR 2024. [Paper]
CoSearchAgent: 基于大型语言模型的轻量级协作搜索代理 - TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision, Zhou et al., SIGIR 2024. [Paper]
TRAD: 通过逐步思维检索和对齐决策增强LLM代理
5.2动态代理
- WebGPT: Browser-assisted question-answering with human feedback, Nakano et al., arXiv 2021. [Paper]
WebGPT: 基于人类反馈的浏览器辅助问答 - WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents, Yao et al., arXiv 2022. [Paper]
WebShop: 基于接地语言代理的可扩展真实世界网页交互 - WebCPM: Interactive Web Search for Chinese Long-form Question Answering, Qin et al., ACL 2023. [Paper]
WebCPM: 中文长篇问答的互动网页搜索 - Mind2Web: Towards a Generalist Agent for the Web, Deng et al., arXiv 2023. [Paper]
Mind2Web: 面向网页的通用代理 - WebArena: A Realistic Web Environment for Building Autonomous Agents, Zhou et al., arXiv 2023. [Paper]
WebArena: 构建自主代理的真实网页环境 - Hierarchical Prompting Assists Large Language Model on Web Navigation, Sridhar et al., EMNLP 2023 (Findings). [Paper]
分层提示辅助大型语言模型进行网页导航 - KwaiAgents: Generalized Information-seeking Agent System with Large Language Models, Pan et al., arXiv 2023. [Paper]
KwaiAgents: 基于大型语言模型的广义信息寻求代理系统 - WebVoyager : Building an End-to-End Web Agent with Large Multimodal Models, He et al., arXiv 2024. [Paper]
WebVoyager : 基于大型多模态模型的端到端网页代理 - AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent, Lai et al., KDD 2024. [Paper]
AutoWebGLM: 基于大型语言模型的网页导航代理的引导与强化 - WebCanvas: Benchmarking Web Agents in Online Environments, Pan et al., arXiv 2024. [Paper]
WebCanvas: 在线环境中网页代理的基准测试 - Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence, Chen et al., arXiv 2024. [Paper]
Internet of Agents: 编织异构代理网络以实现协作智能 - Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems, Abuelsaad et al., arXiv 2024. [Paper]
Agent-E: 从自主网页导航到代理系统基础设计原则 - MindSearch: Mimicking Human Minds Elicits Deep AI Searcher, Chen et al., arXiv 2024. [Paper]
MindSearch: 模仿人类思维激发深度AI搜索者
6.其他资源
- ACL 2023 Tutorial: Retrieval-based Language Models and Applications, Asai et al., ACL 2023. [Link]
ACL 2023 教程: 基于检索的语言模型及其应用 - A Survey of Large Language Models, Zhao et al., arXiv 2023. [Paper]
大型语言模型综述 - Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community, Ai et al., arXiv 2023. [Paper]
信息检索与大型语言模型相遇: 中国IR社区的战略报告