mlsanityData to 7 Oct 2026

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

arXiv 2601.19931 ↗First posted 12 Jan 2026cs.CLcited by 1

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Across self-consistency samples from an LLM, vote agreement tracks instance difficulty: on SemEval-2026 Task 4 (Narrative Story Similarity), supermajority cases (>= 7/8 votes) resolve at 85 percent accuracy, split votes at 67 percent, and perfect ties at 61 percent, a monotone gradient that holds across the development set. We exploit this in CascadeMind, which routes eight Gemini 2.5 Flash votes by consensus, escalates split votes to additional sampling rounds, and falls through to a symbolic ensemble of theory-inspired narrative signals only on perfect ties (5 percent of cases). The system reached 72.75 percent on Track A test, placing 10th of 44 teams. Ablations show that the symbolic component contributes negligibly end-to-end and that nearly all gains come from confidence-aware routing. The takeaway is methodological: for narrative similarity, calibrating when to spend more compute on a hard instance matters more than adding auxiliary representations to reason about it.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 11 of its 36 references that are in the map. First posted on arXiv 12 Jan 2026.

Builds on

11 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs18 Feb

Other references · 10

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  3. 2017Selective Classification for Deep Neural Networkscited by 799
  4. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  5. 2023How is ChatGPT's behavior changing over time?cited by 265
  6. 2016The emotional arcs of stories are dominated by six basic shapescited by 69
  7. 2023Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistencycited by 46
  8. 2024Mirror-Consistency: Harnessing Inconsistency in Majority Votingcited by 16
  9. 2024Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answeringcited by 13
  10. 2022CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understandingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Lacuna Inc. at SemEval-2026 Task 4: Structurally Gated State-Space Models for Disentangling Narrative Similarity
  2. 2026Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction
  3. 2025Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
  4. 2026PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning
  5. 2026COGNAC at SemEval-2026 Task 5: LLM Ensembles for Human-Level Word Sense Plausibility Rating in Challenging Narratives
  6. 2026Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives
  7. 2026SwanNLP at SemEval-2026 Task 5: An LLM-based Framework for Plausibility Scoring in Narrative Word Sense Disambiguation
  8. 2025ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning