Fangyuan Xu
9 papers · 2022–2026 · 5 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(21)
🐣
Hot Topic Early Bird
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Keywords
long-form question answering
(3)
question answering
(3)
large language model
(2)
automatic evaluation
(2)
long-form answer
(2)
information retrieval
(2)
extractive summarization
(1)
text retrieval
(1)
attention mechanism
(1)
instruction following
(1)
text summarization
(1)
semantic similarity
(1)
inference optimization
(1)
evaluation metric
(1)
natural language generation
(1)
semantic annotation
(1)
kv cache
(1)
answer quality
(1)
human evaluation
(1)
retrieval-augmented generation
(1)
Papers
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
EACL 2026
RefreshKV: Updating Small KV Cache During Long-form Generation
ACL 2025
Contrastive Learning to Improve Retrieval for Real-World Fact Checking
EMNLP 2024
KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions
ACL 2024
RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
ICLR 2024
A Critical Evaluation of Evaluations for Long-form Question Answering
ACL 2023
Concise Answers to Complex Questions: Summarization of Long-form Answers
ACL 2023
How Do We Answer Complex Questions: Discourse Structure of Long-form Answers
ACL 2022
Modeling Exemplification in Long-form Question Answering via Retrieval
NAACL 2022