Skip to content
← Back to explorer

CascadeMind at SemEval-2026 Task 4: A Hybrid Neuro-Symbolic Cascade for Narrative Similarity

Sebastien Kawada, Dylan Holyoak · Jan 12, 2026 · Citations: 0

Automatic Metrics
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 2, 2026, 6:18 AM

Recent

Extraction refreshed

Mar 8, 2026, 2:51 AM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.45

Abstract

How should a system handle uncertainty when comparing narratives? We present CascadeMind, a hybrid neuro-symbolic system for SemEval-2026 Task 4 (Narrative Story Similarity) built around a core finding: an LLM's internal vote distribution is a reliable proxy for task difficulty, and confidence-aware routing outperforms uniform treatment of all cases. Our cascade samples eight parallel votes from Gemini 2.5 Flash, applying a supermajority threshold to resolve confident cases immediately (74% of instances at 85% development accuracy). Uncertain cases escalate to additional voting rounds (21%), and only perfect ties (5%) are deferred to a symbolic ensemble of five narrative signals grounded in classical narrative theory. The resulting difficulty gradient (85% -> 67% -> 61% by pathway) confirms that vote consensus tracks genuine ambiguity. In official Track A evaluation, CascadeMind placed 11th of 47 teams with 72.75% test accuracy (Hatzel et al., 2026), outperforming several systems built on larger and more expensive models. Gains are driven primarily by routing strategy rather than symbolic reasoning, suggesting that for narrative similarity, knowing when you don't know matters more than adding auxiliary representations.

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 0.45 (below strong-reference threshold).
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

A benchmark-and-metrics comparison anchor.

Main weakness

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

Trust level

Low

Eval-Fit Score

5/100 • Low

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

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

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: How should a system handle uncertainty when comparing narratives?

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Runtime deterministic fallback evidenced

Includes extracted eval setup.

Evidence snippet: How should a system handle uncertainty when comparing narratives?

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: How should a system handle uncertainty when comparing narratives?

Benchmarks / Datasets

partial

Semeval

Confidence: Low Source: Runtime deterministic fallback evidenced

Useful for quick benchmark comparison.

Evidence snippet: We present CascadeMind, a hybrid neuro-symbolic system for SemEval-2026 Task 4 (Narrative Story Similarity) built around a core finding: an LLM's internal vote distribution is a reliable proxy for task difficulty, and confidence-aware routing outperforms uniform treatment of all cases.

Reported Metrics

partial

Accuracy

Confidence: Low Source: Runtime deterministic fallback evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Our cascade samples eight parallel votes from Gemini 2.5 Flash, applying a supermajority threshold to resolve confident cases immediately (74% of instances at 85% development accuracy).

Rater Population

missing

Unknown

Confidence: Low Source: Runtime deterministic fallback missing

Rater source not explicitly reported.

Evidence snippet: How should a system handle uncertainty when comparing narratives?

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: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.45
  • Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

Semeval

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

We present CascadeMind, a hybrid neuro-symbolic system for SemEval-2026 Task 4 (Narrative Story Similarity) built around a core finding: an LLM's internal vote distribution is a reliable proxy for task difficulty, and confidence-aware… HFEPX signals include Automatic Metrics with confidence 0.45. Updated from current HFEPX corpus.

Generated Mar 8, 2026, 2:51 AM · Grounded in abstract + metadata only

Key Takeaways

  • We present CascadeMind, a hybrid neuro-symbolic system for SemEval-2026 Task 4 (Narrative Story Similarity) built around a core finding: an LLM's internal vote distribution is a…
  • Our cascade samples eight parallel votes from Gemini 2.5 Flash, applying a supermajority threshold to resolve confident cases immediately (74% of instances at 85% development…
  • In official Track A evaluation, CascadeMind placed 11th of 47 teams with 72.75% test accuracy (Hatzel et al., 2026), outperforming several systems built on larger and more…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Cross-check benchmark overlap: Semeval.
  • Validate metric comparability (accuracy).

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 present CascadeMind, a hybrid neuro-symbolic system for SemEval-2026 Task 4 (Narrative Story Similarity) built around a core finding: an LLM's internal vote distribution is a reliable proxy for task difficulty, and confidence-aware…
  • Our cascade samples eight parallel votes from Gemini 2.5 Flash, applying a supermajority threshold to resolve confident cases immediately (74% of instances at 85% development accuracy).
  • In official Track A evaluation, CascadeMind placed 11th of 47 teams with 72.75% test accuracy (Hatzel et al., 2026), outperforming several systems built on larger and more expensive models.

Why It Matters For Eval

  • In official Track A evaluation, CascadeMind placed 11th of 47 teams with 72.75% test accuracy (Hatzel et al., 2026), outperforming several systems built on larger and more expensive models.

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.

  • Pass: Benchmark or dataset anchors are present

    Detected: Semeval

  • Pass: Metric reporting is present

    Detected: accuracy

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