“This post isn't a scientific investigation. It's someone playing around with a black-box model with few to little controls – which is unfortunately the only thing we can do when experimenting with GPT-4, which does excuse this partially. Unfortunately, though, the author seems unaware of the actual state of research on the actual mechanics of how LLMs st…”
Dissecting Recall of Factual Associations in Auto-Regressive Language Models
Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved internally during inference. We investigate this question through the lens of information flow. Given a subject-relation query, we study how the model aggregates information about the subject and relation to predict the correct attribute. With interventions on attention edges, we first identify two critical points where information propagates to the prediction: one from the relation positions followed by another from the subject positions. Next, by analyzing the information at these points, we unveil a three-step internal mechanism for attribute extraction. First, the representation at the last-subject position goes through an enrichment process, driven by the early MLP sublayers, to encode many subject-related attributes. Second, information from the relation propagates to the prediction. Third, the prediction representation "queries" the enriched subject to extract the attribute. Perhaps surprisingly, this extraction is typically done via attention heads, which often encode subject-attribute mappings in their parameters. Overall, our findings introduce a comprehensive view of how factual associations are stored and extracted internally in LMs, facilitating future research on knowledge localization and editing.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- Dissecting Recall of Factual Associations in Auto-Regressive Language Models ↗tosh · 2023-05-01 · 1 分
- Dissecting Recall of Factual Associations in Auto-Regressive Language Models ↗tim_sw · 2023-05-03 · 1 分