[
    {
        "id": "osp-22865",
        "type": "article-journal",
        "title": "Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall",
        "author": [
            {
                "family": "Govindan",
                "given": "Sanjay"
            },
            {
                "family": "Song",
                "given": "Yang"
            },
            {
                "family": "Pagnucco",
                "given": "Maurice"
            }
        ],
        "URL": "https://omanscience.com/en/articles/identifying-temporal-features-within-transcoders-for-time-sensitive-factual-recall",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Large Language Models (LLMs) suffer from temporal misalignment, often due to the contradictory nature of their training corpora. While current mitigation strategies rely on computationally expensive fine-tuning or context-heavy retrieval augmented generation (RAG), the internal mechanisms governing time-sensitive recall remain under-explored. Unlike prior studies that identify temporal components such as attention heads and MLP layers, we provide the first feature-level map of temporal recall by isolating individual MLP features via transcoder circuit tracing. We identify three node categories (common temporal, common to the year, and chrono-semantic) which interact to generate a temporal filter during factual recall. By analysing Gemma 2 2B, LLaMA 3.2 1B, and Qwen3-4B, we show that these features do not follow a simple linear pipeline but represent time through a parallel and mixed syntactic-semantic interplay across layers. We additionally discover a class of higher-layer temporal components invisible to existing EAP-IG methods, establishing transcoders as a more complete lens for temporal interpretability in time-sensitive factual recall. These findings present MLP components for potential targeted interventions in time-sensitive factual recall"
    }
]