MétaCan
Menu
← Back to cohort
Record W6979286200

Towards a Probabilistic Framework for Analyzing and Improving LLM-Enabled Software

2025· article· en· W6979286200 on OpenAlexfundno aff

Bibliographic record

VenuearXiv (Cornell University) · 2025
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsnot available
FundersAgencia Nacional de Promoción Científica y TecnológicaConsejo Nacional de Investigaciones Científicas y TécnicasInternational Development Research CentreUniversidade Federal do AmazonasSecretaría de Ciencia y Técnica, Universidad de Buenos AiresAgencia Nacional de Investigación e Innovación
KeywordsProbabilistic logicIdentification (biology)DocumentationReliability (semiconductor)SoftwareStrengths and weaknessesNatural languageSoftware system
DOInot available

Abstract

fetched live from OpenAlex

Ensuring the reliability and verifiability of large language model (LLM)-enabled systems remains a significant challenge in software engineering. We propose a probabilistic framework for systematically analyzing and improving these systems by modeling and refining distributions over clusters of semantically equivalent outputs. This framework facilitates the evaluation and iterative improvement of Transference Models--key software components that utilize LLMs to transform inputs into outputs for downstream tasks. To illustrate its utility, we apply the framework to the autoformalization problem, where natural language documentation is transformed into formal program specifications. Our case illustrates how distribution-aware analysis enables the identification of weaknesses and guides focused alignment improvements, resulting in more reliable and interpretable outputs. This principled approach offers a foundation for addressing critical challenges in the development of robust LLM-enabled systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.023
metaresearch head score (Gemma)0.065
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.023
Threshold uncertainty score0.120

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0230.065
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0010.004
Bibliometrics0.0060.003
Science and technology studies0.0020.008
Scholarly communication0.0050.011
Open science0.0040.006
Research integrity0.0020.005
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.027
GPT teacher head0.211
Teacher spread0.184 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)→Same topicNatural Language Processing Techniques→French-language works237,207→