Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs. (arXiv:2310.18152v3 [cs.CL] UPDATED)
O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models. (arXiv:2310.14403v3 [cs.AI] UPDATED)
MedAI Dialog Corpus (MEDIC): Zero-Shot Classification of Doctor and AI Responses in Health Consultations. (arXiv:2310.12489v3 [cs.CL] UPDATED)
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model. (arXiv:2309.13018v2 [eess.AS] UPDATED)
TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models. (arXiv:2309.04027v2 [cs.CL] UPDATED)
PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation. (arXiv:2308.12604v2 [cs.CV] UPDATED)
Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge. (arXiv:2308.09311v2 [cs.CV] UPDATED)
Lightweight reranking for language model generations. (arXiv:2307.06857v3 [cs.AI] UPDATED)
Improving Language Plasticity via Pretraining with Active Forgetting. (arXiv:2307.01163v3 [cs.CL] UPDATED)
Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT. (arXiv:2306.01393v3 [cs.CL] UPDATED)
A Comprehensive Evaluation of Neural SPARQL Query Generation from Natural Language Questions. (arXiv:2304.07772v3 [cs.CL] UPDATED)
State-of-the-art generalisation research in NLP: A taxonomy and review. (arXiv:2210.03050v4 [cs.CL] UPDATED)
NAAQA: A Neural Architecture for Acoustic Question Answering. (arXiv:2106.06147v3 [cs.CL] UPDATED)
Machine Translation Models are Zero-Shot Detectors of Translation Direction. (arXiv:2401.06769v1 [cs.CL])
Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements. (arXiv:2401.06766v1 [cs.CL])
APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding. (arXiv:2401.06761v1 [cs.CL])
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies. (arXiv:2401.06760v1 [cs.CL])
Stylometry Analysis of Multi-authored Documents for Authorship and Author Style Change Detection. (arXiv:2401.06752v1 [cs.CL])
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks. (arXiv:2401.06751v1 [cs.CL])
Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain. (arXiv:2401.06742v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl