Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery. (arXiv:2401.06327v1 [cs.CL])
Multi-Task Learning for Front-End Text Processing in TTS. (arXiv:2401.06321v1 [cs.CL])
Zero-shot Generative Large Language Models for Systematic Review Screening Automation. (arXiv:2401.06320v1 [cs.IR])
Beyond the Surface: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation. (arXiv:2401.06310v1 [cs.CV])
Misconfidence-based Demonstration Selection for LLM In-Context Learning. (arXiv:2401.06301v1 [cs.CL])
LEGOBench: Leaderboard Generation Benchmark for Scientific Models. (arXiv:2401.06233v1 [cs.CL])
Learning Unsupervised Semantic Document Representation for Fine-grained Aspect-based Sentiment Analysis. (arXiv:2401.06210v1 [cs.LG])
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction. (arXiv:2401.06201v1 [cs.CL])
CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classification. (arXiv:2401.06194v1 [cs.LG])
End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec2. (arXiv:2401.06183v1 [eess.AS])
Language-based Valence and Arousal Expressions between the United States and China: a Cross-Cultural Examination. (arXiv:2401.05254v2 [cs.CY] UPDATED)
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation. (arXiv:2401.04679v3 [cs.CL] UPDATED)
DebugBench: Evaluating Debugging Capability of Large Language Models. (arXiv:2401.04621v2 [cs.SE] UPDATED)
The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias. (arXiv:2312.16148v3 [cs.CL] UPDATED)
WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation. (arXiv:2312.14187v3 [cs.CL] UPDATED)
Automated speech audiometry: Can it work using open-source pre-trained Kaldi-NL automatic speech recognition?. (arXiv:2312.12269v2 [cs.CL] UPDATED)
Re-parameterized Low-rank Prompt: Generalize a Vision-Language Model within 0.5K Parameters. (arXiv:2312.10813v2 [cs.CV] UPDATED)
Towards Verifiable Text Generation with Evolving Memory and Self-Reflection. (arXiv:2312.09075v2 [cs.CL] UPDATED)
Extending Whisper with prompt tuning to target-speaker ASR. (arXiv:2312.08079v2 [cs.CL] UPDATED)
TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability. (arXiv:2312.06499v2 [cs.CL] UPDATED)
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl