--- title: "blue at SemEval-2026 Task 4 — paper by Sharma et al. (2026)" description: "The authors argue that 512-token encoders such as BERT and RoBERTa often cut off the endings that… 2 references, cited by 1 paper here." authors: ["Krish Sharma", "Lakksh Sharma", "Rhea Singhal", "Jatin Bedi"] year: 2026 venue: "Proceedings of the 20th International Workshop on Semantic Evaluation (2026)" source: "https://aclanthology.org/2026.semeval-1.305/" doi: "10.18653/v1/2026.semeval-1.305" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/sharma-2026-blue-semeval-2026-task-4/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sharma-2026-blue-semeval-2026-task-4/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/10/) / blue at SemEval-2026 Task 4: Synergizing Long-Context Reranking with Semantic Similarity for Narrative Alignment # blue at SemEval-2026 Task 4: Synergizing Long-Context Reranking with Semantic Similarity for Narrative Alignment **Authors:** [Krish Sharma](https://md.research.elamur.ai/free/en/authors/krish-sharma/), [Lakksh Sharma](https://md.research.elamur.ai/free/en/authors/lakksh-sharma/), [Rhea Singhal](https://md.research.elamur.ai/free/en/authors/rhea-singhal/) and [Jatin Bedi](https://md.research.elamur.ai/free/en/authors/jatin-bedi/) · **Year:** 2026 · **Venue:** [Proceedings of the 20th International Workshop on Semantic Evaluation (2026)](https://md.research.elamur.ai/free/en/venues/semeval/) ([SemEval 2026](https://md.research.elamur.ai/free/en/venues/semeval/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.semeval-1.305/) · [PDF](https://aclanthology.org/2026.semeval-1.305.pdf) · [DOI 10.18653/v1/2026.semeval-1.305](https://doi.org/10.18653/v1/2026.semeval-1.305) · [OpenAlex](https://openalex.org/W7166874270) **Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read ## Summary Team blue tackled Track A (Pairwise Similarity) of SemEval-2026 Task 4. Given an anchor story and two candidates, a system must pick the candidate closer in abstract theme, course of action and outcome. The authors argue that 512-token encoders such as BERT and RoBERTa often cut off the endings that carry resolutions and twists, which leaves only shallow lexical comparison. They built a two-stream weighted ensemble: - **Structural stream:** Jina Reranker v2-base-multilingual acts as a cross-encoder over overlapping 1,024-token windows, with max-pooling of chunk scores. - **Semantic stream:** a RoBERTa-Large model (cross-encoder/stsb-roberta-large) produces mean-pooled embeddings compared by cosine similarity. It is meant to catch tonal and stylistic mismatches. The streams are fused with weight α = 0.7 on the structural score. The system used only the official English data. It reached Pearson r = 0.63, and the development-set ablations show gains as reachable context grows. The paper does not report the official primary metric, accuracy. The work suggests that access to story endings drives performance in narrative similarity. ## Key points - **Development-set ablation (Pearson r):** - RoBERTa-Large at 512 tokens: 0.51 - BGE-Large cross-encoder at 512 tokens: 0.56 - Jina Reranker v2 with chunking: 0.59 - Hybrid ensemble: 0.63, which is also the value the paper reports on the official test set - **Fusion weight:** a linear combination with α = 0.7 for the structural score, found by grid search on dev. The authors read this as evidence that long-context structure dominates. - **Setup:** - RoBERTa fine-tuned for 3 epochs, batch 16, LR 2×10⁻⁵ with AdamW, inputs capped at 512 tokens - Jina run in FP16 inference - Code: github.com/Demonn1567/SemEval_Task4 - **Error analysis (50 sampled errors):** - Purely allegorical parallels (e.g., wolfpack vs. boardroom) are missed. - A "satire trap" occurs when an earnest narrative and a mocking version of it follow the same underlying plot. - **Limitations:** - Chunks get no cross-chunk attention. - α may not transfer to other domains. - Cross-lingual ability is untested, since RoBERTa is English-only. - Track B was not attempted. - BGE-M3 was explored but left out of the final system. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Thapar Institute of Engineering & Technology](https://md.research.elamur.ai/free/en/universities/thapar-institute-of-engineering-technology/) — University, Patiāla, India · 6 works · 11 citations 📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works 🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works ## Cite Cite as: Krish Sharma, Lakksh Sharma, Rhea Singhal and Jatin Bedi. 2026. blue at SemEval-2026 Task 4: Synergizing Long-Context Reranking with Semantic Similarity for Narrative Alignment. Proceedings of the 20th International Workshop on Semantic Evaluation (2026). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{sharma2026blue, title = {{blue at SemEval-2026 Task 4: Synergizing Long-Context Reranking with Semantic Similarity for Narrative Alignment}}, author = {Krish Sharma, Lakksh Sharma, Rhea Singhal and Jatin Bedi}, booktitle = {Proceedings of the 20th International Workshop on Semantic Evaluation (2026)}, year = {2026}, doi = {10.18653/v1/2026.semeval-1.305}, url = {https://doi.org/10.18653/v1/2026.semeval-1.305} } ``` - [← previous BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage](https://md.research.elamur.ai/free/en/papers/nakka-2026-bitbypass-new-direction-jailbreaking-aligned/) - [next → BOLT: Benchmarking Open-World Learning for Text Classification](https://md.research.elamur.ai/free/en/papers/qin-2026-bolt-benchmarking-open-world-learning/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/10/) ## References 2 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. [Longformer: The long-document transformer](https://md.research.elamur.ai/free/en/papers/beltagy-2020-longformer-long-document-transformer/). arXiv preprint arXiv:2004.05150. 2. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. BGE M3-embedding: [find](https://scholar.google.com/scholar?q=Jianlv+Chen%2C+Shitao+Xiao%2C+Peitian+Zhang%2C+Kun+Luo%2C+Defu+Lian%2C+and+Zheng+Liu%2E+2024%2E+BGE+M3%2Dembedding%3A) *Updated 31 October 2026*