most citedBenchmarks Saturate When The Model Gets Smarter Than The Judge

1 citations · 1 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG2026

Probing the Trajectories of Reasoning Traces in Large Language Models

Marthe Ballon, Brecht Verbeken, Vincent Ginis +1

Large language models (LLMs) increasingly solve difficult problems by producing "reasoning traces" before emitting a final response. However, it remains unclear how accuracy and de…

cs.LG2026

Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs

Melika Mobini, Vincent Holst, Floriano Tori +2

Large language models are increasingly used to curate bibliographies, raising the question: are their reference lists distinguishable from human ones? We build paired citation grap…

cs.AI20261 cited

Benchmarks Saturate When The Model Gets Smarter Than The Judge

Marthe Ballon, Andres Algaba, Brecht Verbeken +1

Benchmarks are important tools to track progress in the development of Large Language Models (LLMs), yet inaccuracies in datasets and evaluation methods consistently undermine thei…

cs.SI2026

Turning Citation Networks Inside Out: Studying Science Using Content-Based Knowledge Graphs from LLM-Derived Taxonomies

Seorin Kim, Vincent Holst, Vincent Ginis

Scientific fields are often mapped using citations and metadata, despite knowledge being transmitted primarily through content. We introduce an 'inside-out' approach that reconstru…

cs.LG2025

Estimating problem difficulty without ground truth using Large Language Model comparisons

Marthe Ballon, Andres Algaba, Brecht Verbeken +1

Recent advances in the finetuning of large language models (LLMs) have significantly improved their performance on established benchmarks, emphasizing the need for increasingly dif…

cs.CL2025

Lexical Hints of Accuracy in LLM Reasoning Chains

Arne Vanhoyweghen, Brecht Verbeken, Andres Algaba +1

Fine-tuning Large Language Models (LLMs) with reinforcement learning to produce an explicit Chain-of-Thought (CoT) before answering produces models that consistently raise overall…