Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Language Steering for Multilingual In-Context Learning

Neeraja Kirtane, Kuan-Hao Huang

Published

Feb 2, 2026

Citations

0

Trust level

Low

Usefulness score

40/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Apr 1, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Demonstrations Multilingual

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.

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

Best use

Background context only

Use if you need

Background context only.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
40/100
Adjacent candidate

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

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot demonstrations are provided in English but the test query is in a target language. We propose language vectors, computed as the mean activation difference between parallel source and target language examples at a particular layer, and added as an offset to hidden states at inference time to shift the model's internal representations toward the target language. We evaluate our method across three multilingual tasks spanning 19 languages and three models. Our results show consistent improvements on multilingual in-context learning over baselines across all tasks and languages tested, demonstrating that a simple activation offset is sufficient to redirect a model's language mode without any parameter updates. Beyond performance, the vectors encode interpretable linguistic structure, with closely related languages forming tight clusters and vectors transferring across tasks, suggesting that language identity occupies separable and structured directions in a model's activation space.

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

partial

Demonstrations

Directly usable for protocol triage.

"To test this, we take multilingual in-context learning as a case study, where few-shot demonstrations are provided in English but the test query is in a target language."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset."

Quality Controls

missing

Not reported

No explicit QC controls found.

"If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset."

Benchmarks and datasets

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

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Demonstrations
Rater population
Not reported
Expertise required
Multilingual
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset.

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

Key takeaways

  • If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset.
  • To test this, we take multilingual in-context learning as a case study, where few-shot demonstrations are provided in English but the test query is in a target language.
  • We propose language vectors, computed as the mean activation difference between parallel source and target language examples at a particular layer, and added as an offset to hidden states at inference time to shift the model's internal representations toward the target language.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • 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

Contribution summary

  • We propose language vectors, computed as the mean activation difference between parallel source and target language examples at a particular layer, and added as an offset to hidden states at inference time to shift the model's internal…
  • We evaluate our method across three multilingual tasks spanning 19 languages and three models.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Demonstrations

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.