Newest papers

On the Token Collapse Phenomenon in Textual Graph Soft Prompting

Andrea Giuseppe Di Francesco, Rishabh Jain, Franco Maria Nardini, Nicola Tonellotto, Pietro Liò, Fabrizio Silvestri · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31572 · open-access PDF

Arabic

وتشمل الأساليب الحديثة لإدخال هيكل الكاميرا في نصائح LLM إدخال نصائح الكاميرا المفتوحة، حيث تعلم شبكة كاميرا العصبية (GNN) نصائح الكاميرا المفتوحة التي تجمع معلومات العلاقات بين المؤسسات في نصائح النصائح. G-Retriever يجمع نصائح الكاميرا المفتوحة مع وصف مكتوب من نفس الكاميرا لتعزيز إشارة نصائح الكاميرا المفتوحة. نحن نقوم بإجراء تحليل عميق لـ G-Retriever وتحديد السلوك المرضي الذي نسميه فشل نصائح الكاميرا.

Machine translation (Meta M2M100); the English original follows.

Abstract

Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relational information among entities in textual prompts. G-Retriever combines graph soft prompts with a verbalized description of the same graph to strengthen the textual prompt signal. We conduct an in-depth analysis of G-Retriever and uncover a pathological behavior we term token collapse. Across three benchmarks, three graph encoders, two LLM families, and both frozen and LoRA-adapted models, G-Retriever's graph tokens b

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31572, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange