@inproceedings{r-s-ulli-2026-team,
    title = "Team {CV} at {S}em{E}val-2026 Task 4: Prompting {LLM}s and Benchmarking Embedding Models for Narrative Story Similarity",
    author = "R S, Chandan Kumar  and
      Ulli, Vinay",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.374/",
    pages = "2981--2985",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes Team CV{'}s systems forSemEval-2026 Task 4: Narrative Story Sim-ilarity and Narrative Representation Learn-ing (Hatzel et al., 2026). For Track A (com-parative judgment), we explore five prompt-ing strategies{---}zero-shot, chain-of-thought,structured feature extraction, pairwise scor-ing, and few-shot{---}and QLoRA fine-tuningof smaller models. For Track B (narrativeembeddings), we benchmark twelve dedicatedtext embedding models of varying dimen-sionality (384{--}4096) spanning open-source(E5-Large-v2, BGE, GTE, Qwen3 Embed-ding) and closed-source (OpenAI, Gemini,Mistral) families, and fine-tune Qwen3 Em-bedding 4B on task-specific triples. Few-shot prompting with Qwen-2.5 7B (64.00{\%})outperforms all fine-tuned variants (best57.50{\%}) on Track A; scaling to LLaMA-3.3-70B yields 75.00{\%}. On Track B, Ope-nAI text-embedding-3-large (3072-d) achieves the best dev accuracy (67.00{\%}),while fine-tuning Qwen3 Embedding 4B(2560-d) on synthetic triples slightly de-creases accuracy. Our final submission{---}LLaMA-3.3-70B (3-shot) for Track A andtext-embedding-3-large for Track B{---}achieves 70.75{\%} and 64.50{\%}, exceeding theGPT-4o-mini and STORY-EMB baselines respec-tively."
}