Skip to content
← Back to explorer

DRIV-EX: Counterfactual Explanations for Driving LLMs

Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Eric Gaussier · Feb 28, 2026 · 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

Feb 28, 2026, 3:12 PM

Recent

Extraction refreshed

Mar 7, 2026, 12:45 PM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.15

Abstract

Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to alter a driving plan. We introduce DRIV-EX, a method that leverages gradient-based optimization on continuous embeddings to identify the input shifts required to flip the model's decision. Crucially, to avoid the incoherent text typical of unconstrained continuous optimization, DRIV-EX uses these optimized embeddings solely as a semantic guide: they are used to bias a controlled decoding process that re-generates the original scene description. This approach effectively steers the generation toward the counterfactual target while guaranteeing the linguistic fluency, domain validity, and proximity to the original input, essential for interpretability. Evaluated using the LC-LLM planner on a textual transcription of the highD dataset, DRIV-EX generates valid, fluent counterfactuals more reliably than existing baselines. It successfully exposes latent biases and provides concrete insights to improve the robustness of LLM-based driving agents.

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 0.15 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
  • No benchmark/dataset or metric anchors were extracted.
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: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

Validate eval design from full paper text.

Evidence snippet: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque.

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No benchmark anchors detected.

Evidence snippet: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque.

Reported Metrics

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No metric anchors detected.

Evidence snippet: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque.

Rater Population

missing

Unknown

Confidence: Low Source: Runtime deterministic fallback missing

Rater source not explicitly reported.

Evidence snippet: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque.

Human Data Lens

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

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.15
  • 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

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

We propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to alter a driving plan. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Mar 7, 2026, 12:45 PM · Grounded in abstract + metadata only

Key Takeaways

  • We propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to alter a driving plan.
  • We introduce DRIV-EX, a method that leverages gradient-based optimization on continuous embeddings to identify the input shifts required to flip the model's decision.
  • It successfully exposes latent biases and provides concrete insights to improve the robustness of LLM-based driving agents.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Verify metric definitions before comparing against your eval pipeline.

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 propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to alter a driving plan.
  • We introduce DRIV-EX, a method that leverages gradient-based optimization on continuous embeddings to identify the input shifts required to flip the model's decision.
  • It successfully exposes latent biases and provides concrete insights to improve the robustness of LLM-based driving agents.

Why It Matters For Eval

  • It successfully exposes latent biases and provides concrete insights to improve the robustness of LLM-based driving agents.

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.

  • Gap: Metric reporting is present

    No metric terms extracted.

Related Papers

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

No related papers found for this item yet.

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

Post a Job Get a Quote