# Can Large Language Models Address Open-Target Stance Detection? Source: [Can Large Language Models Address Open-Target Stance Detection?]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:02:38.606Z Authors: Abu Ubaida Akash, Ahmed Fahmy, Amine Trabelsi Published: 2024-08-30T19:26:15.000Z ## Abstract Stance detection (SD) identifies the text position towards a target, typically labeled as favor, against, or none. We introduce Open-Target Stance Detection (OTSD), the most realistic task where targets are neither seen during training nor provided as input. We evaluate Large Language Models (LLMs) from GPT, Gemini, Llama, and Mistral families, comparing their performance to the only existing work, Target-Stance Extraction (TSE), which benefits from predefined targets. Unlike TSE, OTSD removes the dependency of a predefined list, making target generation and evaluation more challenging. We also provide a metric for evaluating target quality that correlates well with human judgment. Our experiments reveal that LLMs outperform TSE in target generation, both when the real target is explicitly and not explicitly mentioned in the text. Similarly, LLMs overall surpass TSE in stance detection for both explicit and non-explicit cases. However, LLMs struggle in both target generation and stance detection when the target is not explicit. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Stance Detection on VAST Explicit (test)](): Stance Detection; VAST Explicit (test); SC: 49.84. - [Stance Detection on VAST Non-explicit (test)](): Stance Detection; VAST Non-explicit (test); SC: 0.375. - [Stance Detection on EZSTANCE Explicit (test)](): Stance Detection; EZSTANCE Explicit (test); SC (%): 0.5146. - [Stance Detection on EZSTANCE Non-explicit (test)](): Stance Detection; EZSTANCE Non-explicit (test); SC (%): 48.53. - [Target Generation on EZSTANCE Explicit (test)](): Target Generation; EZSTANCE Explicit (test); SS (SemSim): 89. - [Target Generation on EZSTANCE Non-explicit (test)](): Target Generation; EZSTANCE Non-explicit (test); SS (SemSim): 0.85. - [Target Generation on VAST Explicit (test)](): Target Generation; VAST Explicit (test); SS (SemSim): 0.89. - [Target Generation on VAST Non-explicit (test)](): Target Generation; VAST Non-explicit (test); SemSim Score (SS): 0.85. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()