6 papers
MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators
John Mendonça, Alon Lavie, Isabel Trancoso
Evaluating the quality of open-domain chatbots has become increasingly reliant on LLMs acting as automatic judges. However, existing meta-evaluation benchmarks are static, outdated…
Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs
John Mendonça, Isabel Trancoso, Alon Lavie
Although human evaluation remains the gold standard for open-domain dialogue evaluation, the growing popularity of automated evaluation using Large Language Models (LLMs) has also…
Privacy-oriented manipulation of speaker representations
Francisco Teixeira, Alberto Abad, Bhiksha Raj +1
Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by…
ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues
John Mendonça, Isabel Trancoso, Alon Lavie
Despite being heralded as the new standard for dialogue evaluation, the closed-source nature of GPT-4 poses challenges for the community. Motivated by the need for lightweight, ope…
On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation
John Mendonça, Alon Lavie, Isabel Trancoso
Large Language Models (LLMs) have showcased remarkable capabilities in various Natural Language Processing tasks. For automatic open-domain dialogue evaluation in particular, LLMs…
Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
Francisco Teixeira, Karla Pizzi, Raphael Olivier +3
Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these m…