AI
Benchmarking Patent Drafting from Inventor-Style Disclosures
Researchers have created a new dataset called Dis2Pat to help improve the performance of AI systems in generating patent applications from informal in...
AI
AI
Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning
Researchers have proposed a new framework called Memory-Augmented Compression to improve the efficiency of Chain-of-Thought (CoT) reasoning in large l...
AI
Prompt-Model Interaction Reaches the Fixed Points: A deterministic, task-free structural readout -- and the factorizations of it that failed
Researchers have explored how prompts interact with models, finding that the effect of a prompt is not inherent to the prompt itself. Instead, it's in...
AI
Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy
Researchers have developed an ontology of ten therapeutic moves that large language models (LLMs) use in psychotherapy interactions. They analyzed hum...
AI
A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer
Researchers have created a speech-to-SFT pipeline that can be broken down into its individual stages to study their effectiveness. By toggling certain...
AI
Identify, Locate, Link: End-to-End Key-Value Extraction from Document Images
Researchers from IBM and ETH Zurich have developed an AI model that can directly extract key-value pairs from document images without the need for opt...
AI
MigrationNarrate: A Dataset for Detection of Migration Narratives in YouTube Videos
Researchers have created a dataset called MigrationNarrate to help identify migration narratives in YouTube videos. The dataset includes 1,115 video t...
AI
COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models
Researchers propose a new framework called COMET for video multimodal large language models. The current limitations of these models are addressed by ...
AI
The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models
Researchers studied the internal representations of large language models (LLMs) to understand how they process prompts. They used a method called int...
AI
Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
Researchers have found that large language models (LLMs) used to evaluate code can be biased against certain types of code variations. The study, whic...
AI
Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical Reasoning
Researchers have proposed a new method to evaluate the quality of autoformalization tasks, which involve translating natural language statements into ...
AI
CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis
Researchers have developed a framework called Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) for document-level sentiment anal...