MétaCan
Menu
Back to cohort
Record W4412886783 · doi:10.18653/v1/2025.acl-long.141

Position-aware Automatic Circuit Discovery

2025· article· en· W4412886783 on OpenAlexfundno aff
Tal Haklay, Hadas Orgad, David Bau, Aaron Mueller, Yonatan Belinkov

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Database Systems and Queries
Canadian institutionsnot available
FundersAzrieli FoundationEuropean CommissionOpen Philanthropy Project
KeywordsComputer sciencePosition (finance)Artificial intelligence

Abstract

fetched live from OpenAlex

A widely used strategy to discover and understand language model mechanisms is circuit analysis.A circuit is a minimal subgraph of a model's computation graph that executes a specific task.We identify a gap in existing circuit discovery methods: they assume circuits are position-invariant, treating model components as equally relevant across input positions.This limits their ability to capture cross-positional interactions or mechanisms that vary across positions.To address this gap, we propose two improvements to incorporate positionality into circuits, even on tasks containing variablelength examples.First, we extend edge attribution patching, a gradient-based method for circuit discovery, to differentiate between token positions.Second, we introduce the concept of a dataset schema, which defines token spans with similar semantics across examples, enabling position-aware circuit discovery in datasets with variable length examples.We additionally develop an automated pipeline for schema generation and application using large language models.Our approach enables fully automated discovery of position-sensitive circuits, yielding better trade-offs between circuit size and faithfulness compared to prior work. 1 Belinkov.2021.Causal analysis of syntactic agreement mechanisms in neural language models.

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)0.001
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.008
Threshold uncertainty score0.025

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.010
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.003
Bibliometrics0.0030.003
Science and technology studies0.0010.001
Scholarly communication0.0030.006
Open science0.0030.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0080.003

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 head0.009
GPT teacher head0.247
Teacher spread0.238 · 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 designSimulation or modeling
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 topicAdvanced Database Systems and QueriesFrench-language works237,207