Skip to content
← Back to explorer

What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models

Janiça Hackenbuchner, Arda Tezcan, Joke Daems · Dec 9, 2025 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 4, 2026, 10:01 AM

Recent

Extraction refreshed

Mar 8, 2026, 2:52 AM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.20

Abstract

Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested problem in these models: gender bias. In this work, we aim to move away from simply measuring bias to exploring its origins. Working with gender-ambiguous natural source data, this exploratory study examines which context, in the form of input tokens in the source sentence (EN), influences (or triggers) the NMT model's choice of a certain gender inflection in the target languages (DE/ES). To analyse this, we compute saliency attribution based on contrastive translations. We first address the challenge of the lack of a scoring threshold and specifically examine different attribution levels of source words on the model's gender decisions in the translation. We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution. Additionally, we provide a linguistic analysis of salient words. Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.20 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

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

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

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

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

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

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

No explicit feedback protocol extracted.

Evidence snippet: Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs).

Evaluation Modes

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

Validate eval design from full paper text.

Evidence snippet: Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs).

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs).

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No benchmark anchors detected.

Evidence snippet: Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs).

Reported Metrics

partial

Relevance

Confidence: Low Source: Runtime deterministic fallback evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias.

Rater Population

missing

Unknown

Confidence: Low Source: Runtime deterministic fallback missing

Rater source not explicitly reported.

Evidence snippet: Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs).

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Multilingual
  • Extraction source: Runtime deterministic fallback

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.20
  • Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

relevance

Research Brief

Deterministic synthesis

We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Mar 8, 2026, 2:52 AM · Grounded in abstract + metadata only

Key Takeaways

  • We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution.
  • Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (relevance).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution.
  • Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias.

Why It Matters For Eval

  • We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution.
  • Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • 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: relevance

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote