arXiv:2610. 30518v1 Announce Type: new Abstract: We present Protegrity-PII, a new PII decision model for structured and unstructured text.
We present Protegrity-PII, a new PII decision model for structured and unstructured text. Protegrity-PII achieves a typed recall of 0.915 with a precision of 0.907 on a new benchmark we propose, PII-S...
arXiv:2410.17355v4 Announce Type: replace Abstract: Due to their capacity to acquire world knowledge from large corpora, pre-trained language models (PLMs) are extensively used in ultra-fine entity t...
arXiv:2608. 08636v1 Announce Type: cross Abstract: Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts.
SciNLP is a new benchmark dataset for full‑text entity and relation extraction in the NLP domain, comprising 60 manually annotated papers with 6,429 entities and 1,649 relations. It is the first dataset to provide full‑text annotations of entities and their relationships specifically for NLP literature. Experiments show that models trained on SciNLP outperform baselines on certain tasks, and the dataset enabled the automatic construction of a fine‑grained knowledge graph with an average node degree of 3.3.
arXiv:2610.17113v1 Announce Type: cross Abstract: Information extraction models often perform well on the datasets they are trained on, but transferring to new domains and annotation guidelines remai...
The paper evaluates open‑source large language models (LLMs) for both flat and nested named entity recognition (NER) tasks, comparing them to traditional encoder‑based models and decoder‑based LLMs using in‑context learning. It shows that with parameter‑efficient fine‑tuning and structured output formats (e.g., inline brackets or XML), LLMs can match or exceed the performance of conventional NER systems, and that their NER abilities arise from instruction following rather than memorization. Additionally, fine‑tuning for NER minimally affects, and can even improve, the LLMs’ general capabilities on other benchmarks.
BioBigBird is a bidirectional language model tailored for biomedical text that uses sparse attention to process sequences up to 4096 tokens, addressing the limited context windows of existing domain-specific LLMs. It is pre‑trained on extensive biomedical literature and clinical data, with a multi‑stage training process to reduce noise and a multi‑task learning framework that jointly optimizes Named Entity Recognition and Relation Extraction. Evaluations on the BLURB benchmark show that the MTL‑enhanced BioBigBird achieves highly competitive results against state‑of‑the‑art models, and the models are publicly available on Hugging Face.
arXiv:2607. 17486v1 Announce Type: cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems.
The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.
arXiv:2609.12544v1 Announce Type: new Abstract: Clinical de-identification relies on accurately identifying personally identifiable information (PII). However, manually annotated datasets are costly...
arXiv:2608. 06614v1 Announce Type: cross Abstract: Large-taxonomy retrieval often assumes that the input already expresses the target concept.
The paper introduces STAIR, a retrieval system that uses a document’s Table of Contents to guide large language models in accessing global structure, thereby reducing hallucinations in Retrieval Augmented Generation. Experiments with a fine‑tuned Differentiable Search Index show that ToC‑based retrieval yields a low hallucination rate (<0.05%) and improves Recall@1 to 82.6% on the newly released SearchTome benchmark, outperforming baselines like BM25, DPR, and Mistral. The authors also release SearchTome, a diverse dataset of 18 books across six domains, to encourage further research in ToC‑based retrieval.