Leveraging Professional Radiologists' Expertise to Enhance LLMs' Evaluation for Radiology Reports. (arXiv:2401.16578v1 [cs.CL])
LLMs as On-demand Customizable Service. (arXiv:2401.16577v1 [cs.CL])
Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking. (arXiv:2401.16575v1 [cs.CL])
Autoencoder-Based Domain Learning for Semantic Communication with Conceptual Spaces. (arXiv:2401.16569v1 [cs.LG])
Multi-class Regret Detection in Hindi Devanagari Script. (arXiv:2401.16561v1 [cs.CL])
Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation. (arXiv:2401.16558v1 [cs.CY])
SelectLLM: Can LLMs Select Important Instructions to Annotate?. (arXiv:2401.16553v1 [cs.CL])
GuReT: Distinguishing Guilt and Regret related Text. (arXiv:2401.16541v1 [cs.CL])
InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification. (arXiv:2401.16475v1 [cs.CL])
ReGAL: Refactoring Programs to Discover Generalizable Abstractions. (arXiv:2401.16467v1 [cs.SE])
Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in P2P Lending. (arXiv:2401.16458v1 [q-fin.RM])
KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants. (arXiv:2401.16454v1 [cs.HC])
FaKnow: A Unified Library for Fake News Detection. (arXiv:2401.16441v1 [cs.LG])
An Information Retrieval and Extraction Tool for Covid-19 Related Papers. (arXiv:2401.16430v1 [cs.IR])
Combining topic modelling and citation network analysis to study case law from the European Court on Human Rights on the right to respect for private and family life. (arXiv:2401.16429v1 [cs.IR])
The Power of Noise: Redefining Retrieval for RAG Systems. (arXiv:2401.14887v2 [cs.IR] UPDATED)
MaLLaM -- Malaysia Large Language Model. (arXiv:2401.14680v2 [cs.CL] UPDATED)
Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement. (arXiv:2401.14215v2 [cs.CL] UPDATED)
BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction. (arXiv:2401.14166v2 [cs.CL] UPDATED)
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models. (arXiv:2401.13919v2 [cs.CL] UPDATED)
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl