Nicola Cancedda
25 papers · 2000–2026 · 10 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 9 separate collaboration groups - the largest holds only 36% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Nicola Cancedda?
4 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Karen Hambardzumyan, Roberta Raileanu, Eric Hambro
6 papers
· 2023–2025
· EMNLP, IJCAI, ACL
Hide ▲
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
EMNLP 2025
Combining Code Generating Large Language Models and Self-Play to Iteratively Refine Strategies in Games
IJCAI 2025
HalluLens: LLM Hallucination Benchmark
ACL 2025
Robust LLM safeguarding via refusal feature adversarial training
ICLR 2025
Know When To Stop: A Study of Semantic Drift in Text Generation
NAACL 2024
Toolformer: Language Models Can Teach Themselves to Use Tools
NeurIPS 2023
5 papers whose co-authors appear nowhere else under this name
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
ACL 2026
Spectral Filters, Dark Signals, and Attention Sinks
ACL 2024
Private Access to Phrase Tables for Statistical Machine Translation
ACL 2012
Confidence-Weighted Learning of Factored Discriminative Language Models
ACL 2011
Minimum Error Rate Training by Sampling the Translation Lattice
EMNLP 2010