most citedHow Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders

1 citations · 3 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026★ 1 cited

How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders

Michael McCoubrey, Angelo Salatino, Francesco Osborne +1

In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work. Al…

cs.CL2025★ 1 cited

Modelling and Classifying the Components of a Literature Review

Francisco Bolaños, Angelo Salatino, Francesco Osborne +1

Previous work has demonstrated that AI methods for analysing scientific literature benefit significantly from annotating sentences in papers according to their rhetorical roles, su…