Papers by Luca Zappella
CoRet: Improved Retriever for Code Editing (2025.acl-short)
Copied to clipboard
| Challenge: | Existing encoder models perform poorly in repository-level retrieval for code-editing tasks. |
| Approach: | They propose a loss function for code retrieval that integrates code semantics, repository structure, and call-graph dependencies. |
| Outcome: | The proposed model significantly improves retrieval recall by at least 15 percentage points over existing models on SWE-bench and Long Code Arena’s bug localisation datasets. |
Bias after Prompting: Persistent Discrimination in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Nivedha Sivakumar, Natalie Mackraz, Samira Khorshidi, Krishna Patel, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
| Challenge: | a dangerous assumption is that biases do not transfer from pre-trained large language models to adapted models. |
| Approach: | They validate the bias transfer hypothesis by using prompt adaptations to study biases in causal models . they find that popular prompt-based mitigation methods do not consistently prevent biase transferring . |
| Outcome: | The results invalidate the assumption that biases do not transfer from pre-trained models to adapted models. |
Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results (2025.acl-short)
Copied to clipboard
Andrea Santilli, Adam Golinski, Michael Kirchhof, Federico Danieli, Arno Blaas, Miao Xiong, Luca Zappella, Sinead Williamson
| Challenge: | Language Models (LMs) produce factually incorrect outputs, or "hallucinations" Xiao and Wang et al., 2023) rely on AUROC to assess how well UQ methods distinguish correct from incorrect output. |
| Approach: | They propose to use length biases in correctness functions to skew UQ evaluations . they propose to employ LM-as-a-judge methods as the least length-biased . |
| Outcome: | The proposed method is least length-biased, offering a promising path for a fairer evaluation. |