Suchergebnisse - Lin, Jimmy

Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes? von Lin, Jimmy

Volltext

Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism von Zong, Shi, Lin, Jimmy

Volltext

Revisiting Feedback Models for HyDE von Jedidi, Nour, Lin, Jimmy

Volltext

Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents von Sharifymoghaddam, Sahel, Lin, Jimmy

Volltext

A Systematic Study of Pseudo-Relevance Feedback with LLMs von Jedidi, Nour, Lin, Jimmy

Volltext

Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation von Yang, Jheng-Hong, Lin, Jimmy

Volltext

Illusions of Relevance: Arbitrary Content Injection Attacks Deceive Retrievers, Rerankers, and LLM Judges von Tamber, Manveer Singh, Lin, Jimmy

Volltext

LLMs Can Patch Up Missing Relevance Judgments in Evaluation von Upadhyay, Shivani, Kamalloo, Ehsan, Lin, Jimmy

Volltext

An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking von Chen, Zijian, Pradeep, Ronak, Lin, Jimmy

Volltext

Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM von Sharifymoghaddam, Sahel, Ge, Yijun, Lin, Jimmy

Volltext

Study on LLMs for Promptagator-Style Dense Retriever Training von Gwon, Daniel, Jedidi, Nour, Lin, Jimmy

Volltext

NanoKnow: How to Know What Your Language Model Knows von Gu, Lingwei, Jedidi, Nour, Lin, Jimmy

Volltext

The Trust Paradox: How CS Researchers Engage LLM Leaderboards von Sadeghi, Pouya, Crisan, Anamaria, Lin, Jimmy

Volltext

Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models von Tamber, Manveer Singh, Xian, Jasper, Lin, Jimmy

Volltext

Musings About the Future of Search: A Return to the Past? von Lin, Jimmy, Gupta, Pankaj, Horn, Will, Mishne, Gilad

Volltext

Unifying Adversarial Robustness and Training Across Text Scoring Models von Tamber, Manveer Singh, Oyarhoseini, Hosna, Lin, Jimmy

Volltext

A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation von Oyarhoseini, Hosna, Lin, Jimmy, Karimi, Amir-Hossein

Volltext

UniRAG: Universal Retrieval Augmentation for Large Vision Language Models von Sharifymoghaddam, Sahel, Upadhyay, Shivani, Chen, Wenhu, Lin, Jimmy

Volltext

Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB von Dorbani, Anas, Yasser, Sunny, Lin, Jimmy, Mhedhbi, Amine

Volltext

Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs von Thakur, Nandan, Zhang, Crystina, Ma, Xueguang, Lin, Jimmy

Volltext