Technical Manual for Toolkit for Confidence-Corpus Consistency via Fine-Tuning on a Fabricated Corpus

arXiv:2609.28747v1 Announce Type: cross Abstract: A language model's confidence in an answer is often read as a proxy for how well it knows the corresponding fact. This manual documents an open toolkit built to test that reading directly: a small causal language model is fine-tuned on a corpus that consistently asserts one fabricated arithmetic answer for each of the 81 single-digit addition pairs, and its post-fine-tuning confidence in each fabricated answer is compared against its own pre-fine-tuning confidence in the corresponding true answer, using an unchanged measurement procedure throughout. We describe and justify every pipeline stage, fact-space generation, token-length-aware confidence measurement, baseline validation, corpus construction, fine-tuning, and paired before/after comparison, together with the confound each is meant to rule out, among them tokenization asymmetry between single- and double-digit answers and the difference between an answer merely losing its edge and one being actively suppressed. This manuscript is a methodological and implementation reference: it documents the instrument and does not report or interpret the outcome of any specific run. The toolkit and its pinned dependency environment are archived separately (Section 9) under a persistent identifier, to be cited as an instrument by work that produces and interprets empirical results with it.

Abstract:A language model's confidence in an answer is often read as a proxy for how well it knows the corresponding fact. This manual documents an open toolkit built to test that reading directly: a small causal language model is fine-tuned on a corpus that consistently asserts one fabricated arithmetic answer for each of the 81 single-digit addition pairs, and its post-fine-tuning confidence in each fabricated answer is compared against its own pre-fine-tuning confidence in the corresponding true answer, using an unchanged measurement procedure throughout. We describe and justify every pipeline stage, fact-space generation, token-length-aware confidence measurement, baseline validation, corpus construction, fine-tuning, and paired before/after comparison, together with the confound each is meant to rule out, among them tokenization asymmetry between single- and double-digit answers and the difference between an answer merely losing its edge and one being actively suppressed. This manuscript is a methodological and implementation reference: it documents the instrument and does not report or interpret the outcome of any specific run. The toolkit and its pinned dependency environment are archived separately (Section 9) under a persistent identifier, to be cited as an instrument by work that produces and interprets empirical results with it.

30 pages, 2 figures, 1 table, 12 code listings. Methodological and implementation reference manual; does not report or interpret empirical results from any specific run. Toolkit and pinned dependency environment archived at this https URL (CC BY 4.0)

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2609.28747 [cs.CL]

(or arXiv:2609.28747v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.28747 arXiv-issued DOI via DataCite (pending registration)

analiza aiqbench

Technical Manual for Toolkit for Confidence-Corpus Consistency via Fine-Tuning on a Fabricated Corpus

Subiecte conexe