Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark for mention resolution presented in a multiple-choice question (MCQ) format, commonly used for evaluating LLMs. IdentifyMe features long narratives and employs heuristics to exclude easily identifiable mentions, creating a more challenging task. The benchmark also consists of a curated mixture of different mention types and corresponding entities, allowing for a fine-grained analysis of model performance. We evaluate both closed- and open source LLMs on IdentifyMe and observe a significant performance gap (20-30%) between the state-of-the-art sub-10B open models vs. closed ones. We observe that pronominal mentions, which have limited surface information, are typically much harder for models to resolve than nominal mentions. Additionally, we find that LLMs often confuse entities when their mentions overlap in nested structures. The highest-scoring model, GPT-4o, achieves 81.9% accuracy, highlighting the strong referential capabilities of state-of-the-art LLMs while also indicating room for further improvement.

Our Intelligent-Algorithm is based on the preponderance of progressive and perpetual observation of life signs, presence and multiple physical and biometric digital native attributes of a human subject with time and place references as dynamic components to enroll an unknown and authenticate a known person. Scanning sequences of sensors logical relevance of interaction and relationships between readings, timing and variances as well as soft variables are controlled and processed emulating intuitive human person to person recognition.

Our Intelligent-Algorithm is based on the preponderance of progressive and perpetual observation of life signs, presence and multiple physical and biometric digital native attributes of a human subject with time and place references as dynamic components to enroll an unknown and authenticate a known person. Scanning sequences of sensors logical relevance of interaction and relationships between readings, timing and variances as well as soft variables are controlled and processed emulating intuitive human face to face recognition.