Patrick Lewis
29 papers · 2018–2025 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
🗺️ Taxonomy Completionist (58) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🌟
Keyword Trendsetter Combo
(4)
🤝
Dynamic Duo
(17)
🔬
Deep Specialist
(12)
🧬
Topic Evolution
🧭
Keyword Pioneer
📈
Trend Setter
🗃️
Keyword Collector
(148)
❓
The Questioner
(2)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Natural Language Processing
(25)
Machine Learning
(19)
Applications · Natural Language Processing
(17)
Artificial Intelligence
(16)
Core AI
(13)
Deep Learning
(12)
Core Methods
(9)
Learning Types · Deep Learning
(9)
Learning Types · Machine Learning
(9)
Application Areas
(7)
Resources & Methods
(7)
Generation
(5)
Learning Paradigms
(5)
Computer Science
(3)
Applications · Computer Science
(3)
Keywords
question answering
(6)
dense retrieval
(6)
large language model
(5)
open-domain question answering
(5)
information retrieval
(4)
language model
(4)
knowledge-intensive task
(3)
cross-lingual transfer
(3)
model compression
(3)
retrieval-augmented generation
(3)
extractive question answering
(2)
fact checking
(2)
few-shot learning
(2)
text editing
(2)
unsupervised learning
(2)
seq2seq model
(2)
toxicity mitigation
(2)
domain adaptation
(2)
transfer learning
(2)
passage retrieval
(2)
Papers
FLARE: Faithful Logic-Aided Reasoning and Exploration
EMNLP 2025
EditEval: An Instruction-Based Benchmark for Text Improvements
CoNLL 2024
From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
ACL 2024
MultiContrievers: Analysis of Dense Retrieval Representations
EMNLP 2024
SnapKV: LLM Knows What You are Looking for Before Generation
NeurIPS 2024
Atlas: Few-shot Learning with Retrieval Augmented Language Models
JMLR 2023
ERATE: Efficient Retrieval Augmented Text Embeddings
EACL 2023
Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models
EMNLP 2023
Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training
ACL 2023
On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research
EMNLP 2023
PEER: A Collaborative Language Model
ICLR 2023
Task-aware Retrieval with Instructions
ACL 2023
A Few More Examples May Be Worth Billions of Parameters
EMNLP 2022
Autoregressive Search Engines: Generating Substrings as Document Identifiers
NeurIPS 2022
Boosted Dense Retriever
NAACL 2022
Challenges in Generalization in Open Domain Question Answering
NAACL 2022
Domain-matched Pre-training Tasks for Dense Retrieval
NAACL 2022
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
EMNLP 2022
Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
ICLR 2021
KILT: a Benchmark for Knowledge Intensive Language Tasks
NAACL 2021
Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets
EACL 2021
Dense Passage Retrieval for Open-Domain Question Answering
EMNLP 2020
MLQA: Evaluating Cross-lingual Extractive Question Answering
ACL 2020
Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art
EMNLP 2020
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
NeurIPS 2020
Unsupervised Question Decomposition for Question Answering
EMNLP 2020
Language Models as Knowledge Bases?
EMNLP 2019
Unsupervised Question Answering by Cloze Translation
ACL 2019
Interpretation of Natural Language Rules in Conversational Machine Reading
EMNLP 2018