Jimmy Lin
- Papers
- 43
Cite
Notes
Only stored in your browser.
Authored papers
43Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
arXiv 2026
NanoKnow: How to Know What Your Language Model Knows
arXiv 2026
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?
arXiv 2026
Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality
arXiv 2025
Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
arXiv 2025
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
arXiv 2025
Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval
arXiv 2025
Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
arXiv 2025
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
arXiv 2025
DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers
arXiv 2025
Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation
arXiv 2025
Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses
arXiv 2025
CURE: A dataset for Clinical Understanding & Retrieval Evaluation
arXiv 2024
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
arXiv 2024
UniRAG: Universal Retrieval Augmentation for Large Vision Language Models
arXiv 2024
MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems
arXiv 2024
Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track
arXiv 2024
PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
arXiv 2024
Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard
arXiv 2023
SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
arXiv 2023
RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
arXiv 2023
Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face
arXiv 2023
"Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation
arXiv 2023
GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration
arXiv 2023
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
arXiv 2023
What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations
arXiv 2023
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
arXiv 2023
HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution
arXiv 2023
What the DAAM: Interpreting Stable Diffusion Using Cross Attention
arXiv 2022
Precise Zero-Shot Dense Retrieval without Relevance Labels
arXiv 2022
Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages
arXiv 2022
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval
arXiv 2022
Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study
arXiv 2021
Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval
EMNLP (MRL) 2021 11
Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
arXiv 2021
Showing Your Work Doesn't Always Work
showing-your-work-doesn-t-always-work-1
Inserting Information Bottlenecks for Attribution in Transformers
Findings of the Association for Computational Linguistics 2020
Howl: A Deployed, Open-Source Wake Word Detection System
EMNLP (NLPOSS) 2020 11
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
deebert-dynamic-early-exiting-for-1
The Archives Unleashed Project: Technology, Process, and Community to Improve Scholarly Access to Web Archives
arXiv 2020
End-to-End Open-Domain Question Answering with BERTserini
end-to-end-open-domain-question-answering-1
DocBERT: BERT for Document Classification
arXiv 2019
Deep Residual Learning for Small-Footprint Keyword Spotting
arXiv 2017
Affiliations
Frequent co-authors
10from 43 papers
Xueguang Ma
grad-student
Nandan Thakur
Raphael Tang
Xinyu Zhang
Shengyao Zhuang
Sahel Sharifymoghaddam
Ehsan Kamalloo
Guido Zuccon
Odunayo Ogundepo
Akintunde Oladipo