Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning

Han-yu Wang · May 25, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

Abstract

Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class. We show this hides a sign structure. Under a sign-preserving criterion (refined direct logit attribution, validated head by head with path patching) the FV population splits into two opposing groups: writers push the rule-correct logit up, cancellers push it down, and ablating both together moves the readout less than the sum of the two. The split is causal and reproducible. It holds in all but two of the fifteen (model, task) cells we test, spanning three architectures and six Pythia scales, and a sign-shuffle null rejects the single-class account in all but one of the six main cells. It is also invisible to magnitude-only ranking, which surfaces whichever group locally dominates and misses the other, so any function vector or ablation built that way silently averages a promoting and a suppressing mechanism. Cancellers are not attention sinks, induction heads, or copy-suppression heads, and their causal effect is larger than that of magnitude-matched non-FV controls. Zero-ablating them recovers $+0.13$ to $+0.29$ nats on the correct label in every main cell, and shifts accuracy by $+2$ to $+7$ pp in the same direction.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

  • This paper looks adjacent to evaluation work, but not like a strong protocol reference.
  • The available metadata is too thin to trust this as a primary source.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 35%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"Zero-ablating them recovers $+0.13$ to $+0.29$ nats on the correct label in every main cell, and shifts accuracy by $+2$ to $+7$ pp in the same direction."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Not reported
  • Unit of annotation: Ranking (inferred)
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Low
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracy

Research Brief

Metadata summary

Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • Function-vector (FV) heads are identified by the magnitude of their causal contribution to in-context rule tasks, and the resulting top set is treated as a single functional class.
  • Under a sign-preserving criterion (refined direct logit attribution, validated head by head with path patching) the FV population splits into two opposing groups: writers push the rule-correct logit up, cancellers push it down, and ablating both together moves the readout less than the sum of the two.
  • It holds in all but two of the fifteen (model, task) cells we test, spanning three architectures and six Pythia scales, and a sign-shuffle null rejects the single-class account in all but one of the six main cells.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Accuracy

Research Summary

Contribution Summary

  • We show this hides a sign structure.
  • Zero-ablating them recovers +0.13 to +0.29 nats on the correct label in every main cell, and shifts accuracy by +2 to +7 pp in the same direction.

Why It Matters For Eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.