Skip to content
← Back to explorer

Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation

Bogdan Kostić, Conor Fallon, Julian Risch, Alexander Löser · Feb 19, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Coverage: Stale

Use this page to decide whether the paper is strong enough to influence an eval design. If the signals below are thin, treat it as background context and compare it against the stronger hub pages before making protocol choices.

Paper metadata checked

Feb 19, 2026, 12:24 PM

Stale

Protocol signals checked

Feb 19, 2026, 12:24 PM

Stale

Signal strength

Low

Model confidence 0.25

Abstract

The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison. Yet, their reliability is increasingly questioned due to sensitivity to shallow variations in input prompts. This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA. We employ two linguistically principled pipelines to generate meaning-preserving variations: one performing synonym substitution for lexical changes, and another using dependency parsing to determine applicable syntactic transformations. Results show that lexical perturbations consistently induce substantial, statistically significant performance degradation across nearly all models and tasks, while syntactic perturbations have more heterogeneous effects, occasionally improving results. Both perturbation types destabilize model leaderboards on complex tasks. Furthermore, model robustness did not consistently scale with model size, revealing strong task dependence. Overall, the findings suggest that LLMs rely more on surface-level lexical patterns than on abstract linguistic competence, underscoring the need for robustness testing as a standard component of LLM evaluation.

Use caution before copying this protocol

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 0.25 (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

What We Could Reliably Extract

Each protocol field below shows whether the signal looked explicit, partial, or missing in the available metadata. Use this to judge what is safe to trust directly and what still needs full-paper validation.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.

Benchmarks / Datasets

partial

MMLU, SQuAD

Confidence: Low Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA.

Reported Metrics

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No metric anchors detected.

Evidence snippet: The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Ranking
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.25
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

MMLUSQuAD

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.

Generated Feb 19, 2026, 12:24 PM · Grounded in abstract + metadata only

Key Takeaways

  • The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.
  • Yet, their reliability is increasingly questioned due to sensitivity to shallow variations in input prompts.
  • This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA.

Researcher Actions

  • Compare this paper against others mentioning MMLU.
  • 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

MMLU

Research Summary

Contribution Summary

  • The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.
  • This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA.
  • Overall, the findings suggest that LLMs rely more on surface-level lexical patterns than on abstract linguistic competence, underscoring the need for robustness testing as a standard component of LLM evaluation.

Why It Matters For Eval

  • The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison.
  • This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA.

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.

  • Pass: Benchmark or dataset anchors are present

    Detected: MMLU, SQuAD

  • 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.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now