MétaCan
Menu
Back to cohort

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models

2025· article· W4416036439 on OpenAlexfundno aff
Zeping Yu, Yonatan Belinkov, Sophia Ananiadou

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicMultimodal Machine Learning Applications
Canadian institutionsnot available
FundersAzrieli FoundationEuropean CommissionUniversity of ManchesterOpen Philanthropy Project
KeywordsNatural languageLanguage modelFeature (linguistics)Semantics (computer science)Language understandingAutomated reasoning

Abstract

fetched live from OpenAlex

We investigate how large language models (LLMs) perform latent multi-hop reasoning in prompts like "Wolfgang Amadeus Mozart's mother's spouse is".To analyze this process, we introduce logit flow, an interpretability method that traces how logits propagate across layers and positions toward the final prediction.Using logit flow, we identify four distinct stages in single-hop knowledge prediction: (A) entity subject enrichment, (B) entity attribute extraction, (C) relation subject enrichment, and (D) relation attribute extraction.Extending this analysis to multi-hop reasoning, we find that failures often stem from the relation attribute extraction stage, where conflicting logits reduce prediction accuracy.To address this, we propose back attention, a novel mechanism that enables lower layers to leverage higher-layer hidden states from different positions during attention computation.With back attention, a 1-layer transformer achieves the performance of a 2-layer transformer.Applied to five LLMs, back attention improves accuracy on five reasoning datasets, demonstrating its effectiveness in enhancing latent multi-hop reasoning ability.

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)0.003
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 score0.015
Threshold uncertainty score0.030

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.010
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0020.005
Open science0.0020.003
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.001

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 head0.031
GPT teacher head0.314
Teacher spread0.284 · 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

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicMultimodal Machine Learning ApplicationsFrench-language works237,207