Papers by Ine Gevers
In Benchmarks We Trust ... Or Not? (2025.emnlp-main)
Copied to clipboard
Ine Gevers, Victor De Marez, Jens Van Nooten, Jens Lemmens, Andriy Kosar, Ehsan Lotfi, Nikolay Banar, Pieter Fivez, Luna De Bruyne, Walter Daelemans
| Challenge: | Existing benchmarks for Large Language Models (LLMs) are inadequate and lack a clear solution. |
| Approach: | They propose checklists to cover all aspects of benchmarking issues, both for benchmark creation and usage. |
| Outcome: | The proposed checklists cover all aspects of benchmarking issues, both for benchmark creation and usage. |
Do You Get the Hint? Benchmarking LLMs on the Board Game Concept (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models have achieved impressive progress on many benchmarks, yet they still have fundamental weaknesses. |
| Approach: | They introduce Concept, a word-guessing board game, as a benchmark for probing abductive reasoning. |
| Outcome: | The proposed game is easily solved by humans, but is still very challenging for state-of-the-art LLMs (no model exceeds 40% success rate). |