MétaCan
Menu
Back to cohort
Record W7154608271 · doi:10.48448/tt6v-1975

The emergence of flexible perspective reasoning in large language models

2025· other· W7154608271 on OpenAlexaff
Cognitive Science Society 2025, Craig Chambers, Pablo Leon Villagra, Tiana Simovic

Bibliographic record

VenueUnderline Science Inc. · 2025
Typeother
Language
Field
Topic
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsInterpretabilityPerspective (graphical)Flexibility (engineering)Object (grammar)Antecedent (behavioral psychology)Subject (documents)Point (geometry)Relation (database)Character (mathematics)

Abstract

fetched live from OpenAlex

Work on human reference processing has shown that, in sentences like “Mary asked her daughter Sally if she understood the assignment”, readers overwhelmingly interpret “she” as co-referring with “Sally”. This reflects perspective inference, or reasoning about who possesses at-issue information, and is inconsistent with a statistically-learned bias toward subject antecedent selections. The flexibility of inferencing is evident from the effect of manipulating the object character description (“Mary asked her tutor…”), where readers now prefer Mary as the antecedent. Until recently, these patterns have been largely unaccounted for by large language models (LLMs). Leveraging advancements in LLM interpretability techniques, the present study systematically examines how LLMs fare in relation to human judgments. We determine which layer activations impact these inferences and perturb them to causally link activations to model performance. Finally, we examine performance across training iterations, analyzing the point where subjecthood biases become evident and when more nuanced inferencing emerges.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Insufficient payload (model declined to judge)
Consensus categoriesScience and technology studies, Insufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.930
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0080.003
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0030.013
Science and technology studies0.0010.006
Scholarly communication0.0000.001
Open science0.0050.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0040.001

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 head0.018
GPT teacher head0.336
Teacher spread0.318 · 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; both teacher heads agree on what is shown here.

Study designTheoretical or conceptual
Domainnot available
GenreOther

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 venueUnderline Science Inc.French-language works237,207