ClassEval-Pro benchmark shows frontier LLMs achieve at most 45.6% Pass@1 on class-level code tasks, with logic errors (56%) and dependency errors (38%) as dominant failure modes.
arXiv preprint arXiv:1901.11196 , year =
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
SDBN introduces adversarial training to PEFT via two variants using character-level edits and LLM-generated perturbations, claiming improved robustness and generalization on NLP benchmarks in low-resource noisy settings.
OCL is a governance layer for LLM agents that cuts unsafe executions from 88% to near-zero and raises valid success from 12% to 96% in adversarial buyer-seller negotiations across frontier LLMs.
The paper introduces a new taxonomy that groups AI-driven psychological computing tasks by their underlying computational patterns into four categories and reviews over 300 works from the pre-trained model to LLM eras.
Fin-PRM is a domain-specialized process reward model that supplies binary step-level and trajectory-level supervision signals for financial reasoning in LLMs and outperforms general PRMs on CFLUE and FinQA benchmarks.
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
Contrastive pre-training on unsupervised data at scale creates text and code embeddings that set new state-of-the-art results on classification and semantic search benchmarks.
CPIL is a contrastive two-stage method that enforces paraphrase invariance on limited labeled data to outperform baselines in hallucination detection across 11 tasks.
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.
HAMR combines meta-learning with hardness-aware weighting and neighborhood resampling to improve minority-class performance on imbalanced NLP datasets.
Systematic review of 80 papers shows TTP extraction shifting to transformer and LLM methods but limited by narrow datasets, single-label focus, and low reproducibility.
DeBERTa-V3-base with focal loss, discourse features, and LLM-augmented data for minority classes achieves 0.76 Macro F1 on clarity-level classification of political QA pairs, ranking 8th in SemEval-2026 Task 6.
Fine-tuning and data augmentation improve LLM performance on medical jargon extraction and prioritization from EHR notes, with augmented open-source models sometimes outperforming closed-source ones on 106 annotated notes.
Transformer models with class weighting and threshold tuning achieve competitive F1 scores on three subtasks of multilingual polarization detection.
A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizing generative technologies.
citing papers explorer
-
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
-
Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning
SDBN introduces adversarial training to PEFT via two variants using character-level edits and LLM-generated perturbations, claiming improved robustness and generalization on NLP benchmarks in low-resource noisy settings.
-
Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models
Fin-PRM is a domain-specialized process reward model that supplies binary step-level and trajectory-level supervision signals for financial reasoning in LLMs and outperforms general PRMs on CFLUE and FinQA benchmarks.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
Text and Code Embeddings by Contrastive Pre-Training
Contrastive pre-training on unsupervised data at scale creates text and code embeddings that set new state-of-the-art results on classification and semantic search benchmarks.
-
Cross Paraphrastic Invariance Learning for Hallucination Detection
CPIL is a contrastive two-stage method that enforces paraphrase invariance on limited labeled data to outperform baselines in hallucination detection across 11 tasks.
-
Duluth at SemEval-2026 Task 6: DeBERTa with LLM-Augmented Data for Unmasking Political Question Evasions
DeBERTa-V3-base with focal loss, discourse features, and LLM-augmented data for minority classes achieves 0.76 Macro F1 on clarity-level classification of political QA pairs, ranking 8th in SemEval-2026 Task 6.
-
Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation
Fine-tuning and data augmentation improve LLM performance on medical jargon extraction and prioritization from EHR notes, with augmented open-source models sometimes outperforming closed-source ones on 106 annotated notes.
-
Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning
Transformer models with class weighting and threshold tuning achieve competitive F1 scores on three subtasks of multilingual polarization detection.