Picture for Alon Lavie

Alon Lavie

School of Computer Science, Carnegie Mellon University

Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs

Add code
Aug 20, 2024
Viaarxiv icon

ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues

Add code
Jul 16, 2024
Viaarxiv icon

On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation

Add code
Jul 04, 2024
Viaarxiv icon

Dialogue Quality and Emotion Annotations for Customer Support Conversations

Add code
Nov 23, 2023
Viaarxiv icon

Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation

Add code
Sep 08, 2023
Viaarxiv icon

Towards Multilingual Automatic Dialogue Evaluation

Add code
Aug 31, 2023
Viaarxiv icon

The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics

Add code
May 19, 2023
Viaarxiv icon

Appropriateness is all you need!

Add code
Apr 27, 2023
Viaarxiv icon

CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task

Add code
Sep 13, 2022
Figure 1 for CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
Figure 2 for CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
Figure 3 for CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
Figure 4 for CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
Viaarxiv icon

Unbabel's Participation in the WMT20 Metrics Shared Task

Add code
Oct 29, 2020
Figure 1 for Unbabel's Participation in the WMT20 Metrics Shared Task
Figure 2 for Unbabel's Participation in the WMT20 Metrics Shared Task
Figure 3 for Unbabel's Participation in the WMT20 Metrics Shared Task
Figure 4 for Unbabel's Participation in the WMT20 Metrics Shared Task
Viaarxiv icon