ACL 2026 — NLP Applications

NLP Applications

32 papers Links not yet available — ACL proceedings pending on ACL Anthology.

• Logic Matters in Lightweight Hallucination Classification for RAG System
• What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification
• Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
• SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification
• Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects
• LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues
• Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER
• Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis
• MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
• Label and Explanation Variation in LLM-Based Annotation: a Case Study in Natural Language Inference
• MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis
• TLSA: LLM-Guided Text-Label Space Alignment with Contrastive Learning for Generalized Category Discovery
• Uncovering Sentiment Analysis Circuit in Large Language Model
• Mitigating Spurious Correlations in Text Classification Using Latent Space Geometry
• Fair-CCD: Mitigating Bias in Large Language Models for Tabular Classification Through Context-Contrastive Decoding
• LGSA: Label Geometry Structuring and Aligning for Hierarchical Text Classification
• CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
• An Experimental Study on the Influence of Culture on Cross-Lingual Sentiment Transfer
• QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis
• Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
• Beyond Single Representations: Multi-Model Embedding Fusion for Stable Text Classification
• Towards Fast and Accurate Modeling for Cross-Lingual Label Projection
• Deep Supervised Contrastive Learning of Pitch Contours for Robust Pitch Accent Classification in Seoul Korean
• DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis
• Beyond Static Alignment: Adaptive Arbitration for Semantic Incongruence in Semi-Supervised Multimodal Sentiment Analysis
• A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
• BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels
• HSGraphAgent: Knowledge-Graph-Guided Large Language Models for Harmonized System Code Classification
• Adversarial Metric Learning for Fine-Grained Emotion Classification
• When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score
• MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events
• SELECting over Tokens: Curating Pre-training Data at Scale via Token Classification