{"slug": "lexical-coupling-in-gui-element-grounding-sentence-embeddings-track-labels-and", "title": "Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web", "summary": "A new arXiv preprint (2608.21794v1) finds that GUI grounding evaluations using sentence embeddings often conflate visible-label recovery with semantic grounding, as lexical baselines remain competitive at top-1 across three mobile and web benchmarks. The authors recommend reporting lexical baselines, label-type stratification, and deployable-fusion diagnostics, and release analysis scripts at https://github.com/qijia123/lexical-coupling-release.", "body_md": "arXiv:2608.21794v1 Announce Type: new\nAbstract: GUI grounding evaluations that expose UI elements as text metadata often treat high instruction-element embedding similarity as evidence of semantic grounding. Across three mobile and web benchmarks, we show that this interpretation is frequently confounded by visible-label recovery. Lexical baselines remain competitive at top-1, label-poor targets remain weak for text-only methods, and encoder top-1 hits are predictable from lexical rank, candidate-pool size, and label type. We evaluate each action as a same-screen ranking task, comparing five off-the-shelf single-vector encoders with lexical baselines. Encoders recover some lexical misses, but deployable fusion gains are much smaller than target-aware oracle gains. These findings show that embedding-based evaluations can conflate visible-label recovery with semantic GUI grounding. Embedding-based evaluations should therefore report lexical baselines, label-type stratification, and deployable-fusion diagnostics. Our released repository provides analysis scripts and detexted per-step panels: https://github.com/qijia123/lexical-coupling-release.", "url": "https://wpnews.pro/news/lexical-coupling-in-gui-element-grounding-sentence-embeddings-track-labels-and", "canonical_source": "https://arxiv.org/abs/2608.21794", "published_at": "2026-08-25 04:00:00+00:00", "updated_at": "2026-08-25 04:15:36.738217+00:00", "lang": "en", "topics": ["natural-language-processing", "machine-learning"], "entities": ["arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/lexical-coupling-in-gui-element-grounding-sentence-embeddings-track-labels-and", "markdown": "https://wpnews.pro/news/lexical-coupling-in-gui-element-grounding-sentence-embeddings-track-labels-and.md", "text": "https://wpnews.pro/news/lexical-coupling-in-gui-element-grounding-sentence-embeddings-track-labels-and.txt", "jsonld": "https://wpnews.pro/news/lexical-coupling-in-gui-element-grounding-sentence-embeddings-track-labels-and.jsonld"}}