Researchers have proposed a new method called SeqFeed to improve the generation of RTL (Register-Transfer Level) code in hardware design. This process...
Researchers have developed a method called J-Miner to extract decision-making knowledge from large language models. These models can be fine-tuned for...
Researchers have found a way to bypass defenses in large language model services by splitting harmful tasks into smaller, individually permissible req...
Researchers have proposed a new approach to parsing academic documents called Compilable Academic Document Parsing (CADP). This method reconstructs a ...
Researchers have developed Reflex-Guard, a lightweight guardrail for Large Language Models (LLMs) that detects unsafe prompts with low latency. Unlike...
Researchers have investigated the problem of specifying a reward function for large language models (LLMs) to unlearn target-specific knowledge. They ...
Researchers have been critical of word embeddings, which are used to represent words as vectors, for capturing undesirable associations such as gender...
Researchers have analyzed the frequency of grammar errors in Esperanto using a dataset created specifically for this purpose. They also introduced ano...
Researchers propose SimulRAG, a framework that uses scientific simulators to improve the accuracy of long-form scientific question answering. This is ...
Researchers have developed a new method for extracting semi-structured data from web pages. SCRIBES uses reinforcement learning to generate reusable s...
Researchers have developed a new framework called Dripper for efficiently extracting main content from web pages. Unlike traditional methods that rely...
Researchers at UC Davis and Virginia Tech have studied how large language models learn and forget concepts during continuous training. They found that...