The paper evaluates nine on‑device named‑entity recognition models ranging from classical taggers to large language models, measuring not only accuracy but also latency and output validity. Using a silver‑gold benchmark derived from an LLM judge panel and a human‑validated corpus, the study shows that encoder‑based models achieve comparable accuracy to a 4 B instruct LLM while being much smaller, faster, and producing no malformed output. Confidence calibration of GLiNER is analyzed, revealing over‑confidence but improved reliability after temperature scaling and thresholding.
By Vinay Kumar Chaganti
The paper investigates a failure mode in Graph-JEPA, a joint‑embedding predictive model trained on a large scientific‑reasoning graph. Despite achieving high linear‑probe accuracy and effective rank, the learned representation contains almost no usable instance information, as shown by retrieval metrics. The authors diagnose the issue to variance allocation in the objective, propose a repair that restores near‑perfect information recovery, and demonstrate that the problem persists even after repair, highlighting limitations in the evaluation metrics used.
By Gollam Rabby, S\"oren Auer
arXiv:2606. 24948v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) models predict single-hop links well but have no mechanism for zero-shot compositional queries: multi-hop questions whose relation chains never appeared during training.
By Randhir Kumar
arXiv:2609.09001v1 Announce Type: new
Abstract: Multi-step LLM reasoning lacks a machine-recheckable ledger: discarded reasoning paths leave no auditable record. We propose the Deposon scattering lay...
By Qihao Yuan
arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.
By Hiskias Dingeto
arXiv:2605. 21510v2 Announce Type: replace-cross Abstract: Reference-based graph compression encodes each vertex's neighbor list as differences from a nearby encoded list.
By Jimmy Dubuisson
arXiv:2609.37604v1 Announce Type: new
Abstract: Graph foundation models need a discrete token representation, but casting a graph as a generatable token sequence faces a structural obstacle: edges sp...
By Yuxiang Yao, Zijun Zhao
CropCop is a closed‑set plant‑health recognition system covering 120 operational classes, built from a rigorously audited dataset of 109,107 images after removing 3,233 duplicate relationships. The model, based on a fine‑tuned DINOv3 ConvNeXt‑Tiny, achieves 98.51% accuracy and 96.87% macro‑F1 on a locked internal test, while a quantised MobileNetV4 variant reaches 98.46% accuracy and 96.23% macro‑F1 in a 22.60 MiB runtime artifact. Validation‑only post‑training quantisation and a compact ExecuTorch/XNNPACK PTE ensure high fidelity between the trained model and its deployed form, with minimal decision changes between the INT8 graph and the final artifact.
By Rana Muhammad Ahmed, Sabahat Abbas
arXiv:2606. 02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest.
By Aizierjiang Aiersilan
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
By Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh
arXiv:2608. 08139v1 Announce Type: new Abstract: Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challenge that metadata alone cannot resolve.
By Yuqi Wu, Shengming Zhao, Jie Chen
arXiv:2601. 00821v3 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts -- extracted facts, decisions, or events -- on the premise that distilled structure retrieves better than raw text.
By Tao An