Tag
The paper proposes dLLM-SetScore, a training-free framework using discrete masked-diffusion language models for multi-label text classification, achieving competitive performance with minimal validation data.
Liquid AI fine-tuned their LFM2.5-Encoder models (230M and 350M) to perform multi-label classification in a single forward pass, eliminating the need for decoding loops or parsing. This demonstrates efficient label scoring for NLP tasks.
Proposes a deep neural model combining multi-layer temporal convolutional networks with label-wise attention for medical coding, achieving significant improvements in F1 and recall scores over previous state-of-the-art.
This paper presents a reproducible pipeline for mapping CVEs to MITRE ATT&CK techniques using a curated gold dataset, and investigates the limits of using LLM-assisted labeling to expand training data, finding that LLM-generated labels do not reliably improve performance due to evaluation noise and label quality issues.
This paper explores machine learning approaches, including encoder-based models and fine-tuned LLMs, for automatic thematic indexing of large literary corpora, using Voltaire's complete works as a test case. The best model achieves F1 scores up to 0.67, with implications for structured access to large-scale literary and historical editions.
This paper presents UCSC NLP's systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction using boundary-aware span extraction with RoBERTa, and document-level conspiracy classification with label smoothing. The systems ranked 7th in subtask 1 and 12th in subtask 2.
This paper presents CaresAI's approach to the SMM4H-HeaRD 2026 shared task on predicting TNM staging from pathology reports using various embeddings and classifiers, achieving strong results but noting generalization issues.
This paper formulates multi-agent routing as set-valued prediction, introduces a WildChat-derived benchmark with 3,000 prompts over a 12-agent catalog, and evaluates methods including supervised classifiers and cost-aware routing to study accuracy-cost trade-offs.
This paper presents the first unified benchmark for pathway-guided therapy response modeling, evaluating three biologically informed architectures (BINN, GraphPath, PATH) across five cancer cohorts from The Cancer Genome Atlas for multi-label prediction of targeted therapy, radiation therapy, and survival outcomes.
This paper investigates how reasoning models perform zero-shot multi-label classification over millions of candidate labels. The authors characterize a two-phase process of shortlisting and fine-grained reasoning, and propose a mechanistic distillation method that outperforms standard distillation for transferring these capabilities to smaller models.