Papers by Nicola Cancedda

7 papers
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation (2026.acl-industry)

Copied to clipboard

Challenge: Existing methods for obtaining well-calibrated uncertainty estimates are poorly calibrated or computationally expensive.
Approach: They propose a linear probe that provides calibrated uncertainty estimates from reasoning judges’ hidden states, requiring no additional model training.
Outcome: The proposed method achieves superior calibration compared to existing methods with x computational savings, generalizes robustly to unseen evaluation domains, and delivers higher accuracy on high-confidence predictions.
Spectral Filters, Dark Signals, and Attention Sinks (2024.acl-long)

Copied to clipboard

Challenge: Recent work assigns a central role to the model's residual stream as the shared communication channel between model components.
Approach: They propose a quantitative extension of the logit lens approach by partitioning the embedding and unembedding matrices into bands and spectral filters on intermediate representations.
Outcome: The proposed model can suppress the tail end of the embedding spectrum, but it is not able to suppress large parts of the spectrum.
EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing (2022.emnlp-main)

Copied to clipboard

Challenge: Existing work on Entity Linking assumes that the knowledge base is complete and all mentions can be linked.
Approach: They propose a temporally segmented Unknown Entity Discovery and Indexing (EDIN) benchmark where unknown entities have to be integrated into existing entity linking systems.
Outcome: The proposed system detects, clusters, and indexes mentions of unknown entities in context.
Multilingual Autoregressive Entity Linking (2022.tacl-1)

Copied to clipboard

Challenge: mGENRE is a sequence-to-sequence system for multilingual entity linking . mGenRE is used to solve language-specific mentions to a multilingual Knowledge Base .
Approach: They propose a sequence-to-sequence system for multilingual entity linking . they match language-specific mentions against a multilingual Knowledge Base (KB) mGENRE is a sequential system that predicts the name of the target entity token-by-token .
Outcome: The proposed system improves on three popular MEL benchmarks and shows improvements in accuracy.
HalluLens: LLM Hallucination Benchmark (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) generate responses that deviate from user input or training data, a phenomenon known as "hallucination" .
Approach: They propose a hallucination benchmark HalluLens that includes both extrinsic and intrinsic evaluation tasks to distinguish between extrindic and intrinsic hallucines.
Outcome: The proposed framework disentangles LLM hallucination from "factuality" and distinguishes between extrinsic and intrinsic hallucines to promote consistency and facilitate research.
Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings (2023.emnlp-main)

Copied to clipboard

Challenge: Entity linking methods based on dense retrieval are often not efficient in large-scale applications as they are sensitive to the structure of the embedding space.
Approach: They propose a method to infuse structural information into the space of entity representations by using prior knowledge of entity types.
Outcome: The proposed method outperforms other type-aware approaches and matches generative models with 18 times more parameters.
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations (2025.emnlp-main)

Copied to clipboard

Challenge: LLMs often use assertive language when making false claims, resulting in harm and loss of trust.
Approach: They find that a mismatch between semantic and verbal uncertainty is a better predictor of hallucinations than semantic uncertainty alone.
Outcome: a new study shows that mismatch between semantic and verbal uncertainty is better predictor of hallucinations than semantic uncertainty alone.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations