AI
KA2L: A Knowledge-Aware Active Learning Framework for LLMs
Researchers have developed a framework called KA2L to improve the performance of large language models (LLMs) by assessing their knowledge and focusin...
AI
AI
Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
Large language models (LLMs) are becoming increasingly costly and difficult to improve through human supervision alone. As they approach human-level c...
AI
Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering
Researchers from the University of Tel Aviv have proposed a method to predict whether incorporating external information into question-answering syste...
AI
An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection
Researchers have proposed a new framework called InfoPDF to improve the accuracy of fake news detection. The framework uses a combination of real and ...
AI
Tatarstan Toponyms: A Bilingual Dataset and Hybrid RAG System for Geospatial Question Answering
A new dataset of Russian and Tatar toponyms (place names) has been created, containing over 9,600 entries with linguistic, etymological, and coordinat...
AI
CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law
Researchers have created a new benchmark for evaluating the performance of retrieval-augmented generation (RAG) models on Canadian case law. The CanLe...
AI
Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models
Researchers have developed a new method to mitigate hallucinations in large language models. Hallucinations occur when the model generates responses t...
AI
Hallucination Detection in Large Language Models Using Diversion Decoding
Researchers have developed a new method to detect hallucinations in large language models (LLMs). Hallucinations occur when LLMs generate factually in...
AI
ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives
Researchers have created a dataset called ConstructCIE to help extract causal information from narratives about construction accidents. The dataset in...
AI
X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction
Researchers have developed a new method for spoken dialogue systems to predict when a user has finished speaking. The approach, called X2-Turn, uses a...
AI
How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks
Researchers have introduced a new evaluation framework called AutoResearchEval to assess the performance of AI agents in carrying out scientific resea...
AI
LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
Researchers have developed LACONIC, a family of learned sparse retrievers that can efficiently search large datasets using commodity CPU hardware. Unl...