Sohee Yang
20 papers · 2019–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Academic Marathon (6) π Conference Polyglot (8) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (3)
π
Cross-Pollinator
(3)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(43)
π€
Dynamic Duo
(11)
π§¬
Topic Evolution
π₯
Unstoppable
(7)
β
The Questioner
(4)
π
Century Club
(19)
ποΈ
Keyword Collector
(75)
β‘
Prolific Year
(5)
Conferences
ACL (6)
EMNLP (5)
ICLR (2)
IJCNLP (2)
AAAI (1)
AACL (1)
INTERSPEECH (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
large language model
(8)
multi-hop reasoning
(3)
latent reasoning
(3)
knowledge retrieval
(3)
generative retrieval
(3)
information retrieval
(2)
document retrieval
(2)
language model
(2)
reinforcement learning
(2)
safety alignment
(2)
dialogue state tracking
(1)
knowledge unlearning
(1)
model safety
(1)
model interpretability
(1)
transfer learning
(1)
sequence modeling
(1)
zero-shot generalization
(1)
instruction following
(1)
continual learning
(1)
temporal alignment
(1)
Papers
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?
EMNLP 2025
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
ACL 2025
Building Helpful-Only Large Language Models: A Complete Approach from Motivation to Evaluation
AACL 2025
Building Helpful-Only Large Language Models: A Complete Approach from Motivation to Evaluation
IJCNLP 2025
Exploring the Practicality of Generative Retrieval on Dynamic Corpora
EMNLP 2024
Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following
AAAI 2024
Do Large Language Models Latently Perform Multi-Hop Reasoning?
ACL 2024
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
NIPS 2024
Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries
EMNLP 2024
Knowledge Unlearning for Mitigating Privacy Risks in Language Models
ACL 2023
Nonparametric Decoding for Generative Retrieval
ACL 2023
Generative Multi-hop Retrieval
EMNLP 2022
Towards Continual Knowledge Learning of Language Models
ICLR 2022
TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
EMNLP 2022
Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering
NAACL 2021
Spatial Dependency Parsing for Semi-Structured Document Information Extraction
IJCNLP 2021
Spatial Dependency Parsing for Semi-Structured Document Information Extraction
ACL 2021
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers
INTERSPEECH 2020
Efficient Dialogue State Tracking by Selectively Overwriting Memory
ACL 2020
Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation
ICLR 2019