MétaCan
Menu
← Back to cohort

The Mystery of the Pathological Path-star Task for Language Models

2024· article· en· W4404792915 on OpenAlexafffund
Arvid Frydenlund

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsVector Institute
FundersStrongGovernment of CanadaCanadian Institute for Advanced Research
KeywordsTask (project management)Computer sciencePath (computing)Star (game theory)Artificial intelligenceNatural language processingProgramming languageEngineeringAstrophysicsPhysics

Abstract

fetched live from OpenAlex

The recently introduced path-star task is a minimal task designed to exemplify limitations to the abilities of language models (Bachmann and Nagarajan, 2024).It involves a path-star graph where multiple arms radiate from a single starting node and each node is unique.Given the start node and a specified target node that ends an arm, the task is to generate the arm containing that target node.This is straightforward for a human but surprisingly difficult for language models, which did not outperform the random baseline.The authors hypothesized this is due to a deficiency in teacher-forcing and the next-token prediction paradigm.We demonstrate the task is learnable using teacher-forcing in alternative settings and that the issue is partially due to representation.We introduce a regularization method using structured samples of the same graph but with differing target nodes, improving results across a variety of model types.We provide RASP proofs showing the task is theoretically solvable.Finally, we find settings where an encoder-only model can consistently solve the task.

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)0.007
metaresearch head score (Gemma)0.041
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.040

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.041
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0020.005
Scholarly communication0.0030.014
Open science0.0030.004
Research integrity0.0040.011
Insufficient payload (model declined to judge)0.0060.003

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 head0.016
GPT teacher head0.273
Teacher spread0.257 · 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 designBench or experimental
Domainnot available
GenreEmpirical

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
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicNatural Language Processing Techniques→French-language works237,207→