Textual spatial semantic anomaly detection and attribution requires deciding whether a sentence contains an implausible spatial relation and assigning the corresponding attribution label. Prior prompting and Low-Rank Adaptation (LoRA) fine-tuning methods rely on raw tokenlevel representations, leaving spatial roles and cross-triple conflicts implicit. We propose SCP-ISA, a Spatial Cross-attention Projection (SCP) method with an Inter-Slot Attention (ISA) layer that uses a frozen MacBERT-large encoder to build input-conditioned spatial slots and injects the projected slots into Qwen2.5 as soft prefix embeddings. The ISA layer enables structured cross-slot interaction that collapses co-referring spatial mentions into a shared entity-anchored representation before generation. On the CRSARC benchmark, SCP-ISA improves test cascade attribution F1 (Attr-F1) by 22.7 percentage points (0.509 to 0.736) over Direct LoRA, and detection macro-F1 (Det-F1) from 0.846 to 0.881.

Users usually browse product reviews before buying products from e-commerce websites. Lots of e-commerce websites can recommend reviews. However, existing research on review recommendation mainly focuses on the general usefulness of reviews and ignores personalized and implicit requirements. To address the issue, we propose a Large language model driven Personalized Review Recommendation model based on Implicit dimension mining (PRR-LI). The model mines implicit dimensions from reviews and requirements, and encodes them in the form of “text + dimension”. The experiments show that our model significantly outperforms other state-of-the-art textual models on the Amazon-MRHP dataset, with some of the metrics outperforming the state-of-the-art multimodal models. And we prove that encoding “text + dimension” is better than encoding “text” and “dimension” separately in review recommendation.