Tomasz Jan Kajdanowicz
7 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)
❓
The Questioner
Conferences
ACL (4)
EMNLP (2)
EACL (1)
Top co-authors
Keywords
large language model
(3)
hallucination detection
(3)
graph neural network
(2)
graph structure
(1)
eigenvalue decomposition
(1)
performance evaluation
(1)
spectral analysis
(1)
knowledge graph
(1)
hidden state
(1)
benchmark dataset
(1)
evaluation metric
(1)
sampling method
(1)
retrieval-augmented generation
(1)
attention map
(1)
human evaluation
(1)
laplacian eigenvalue
(1)
dialogue system
(1)
semantic vector space
(1)
legal document
(1)
semantic evaluation
(1)
Papers
FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs
EACL 2026
Beyond Discrete Search: Divergent Thinking as Intention Optimization in Latent Space
ACL 2026
Factual State Discovery Benchmark: Evaluating Fact Elicitation in Polish Tax Law
ACL 2026
Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models
ACL 2026
Hallucination Detection in LLMs Using Spectral Features of Attention Maps
EMNLP 2025
The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs
EMNLP 2025
When Will the Tokens End? Graph-Based Forecasting for LLMs Output Length
ACL 2025