IsoBench evaluates how models handle text and images to identify strengths.
― 3 min read
Cutting edge science explained simply
IsoBench evaluates how models handle text and images to identify strengths.
― 3 min read
Discover the processes behind training advanced AI language models.
― 6 min read
Examines the growth of communication between humans and robots using natural speech.
― 7 min read
Exploring how benign data can unintentionally produce harmful outputs in language models.
― 4 min read
This paper examines models solving tricky brain teasers in natural language processing.
― 6 min read
Exploring the role of ethics in language translation technology.
― 5 min read
A new method to assess the accuracy of language models using knowledge graphs.
― 7 min read
ChatGLM-RLHF improves AI interactions through human feedback and advanced training methods.
― 5 min read
A new dataset focuses on causal reasoning using 'Tom and Jerry' animations.
― 6 min read
Introducing a framework for more accurate query performance assessment in information retrieval.
― 6 min read
Research reveals significant security risks in chat models from backdoor attacks.
― 6 min read
This study assesses the performance of LLMs with the Persian language.
― 4 min read
Research highlights vulnerabilities of MNMT systems to backdoor attacks.
― 7 min read
A study on how T5 processes structured data for SQL queries.
― 11 min read
A new approach to protect language models from harmful data triggers.
― 7 min read
Exploring the intersection of quantum computing and transformer models in AI.
― 6 min read
Explore how Mixture-of-Depths improves language model efficiency sustainably.
― 7 min read
Study shows smaller models perform well with simplified training data.
― 6 min read
This study investigates using AI to create distractors for math multiple-choice questions.
― 5 min read
A new approach to improve topic modeling using graph-based relations.
― 7 min read
A new dataset measures RAG systems for accurate question answering.
― 6 min read
New models enhance reasoning skills across various tasks, improving AI performance.
― 6 min read
This guide explores integrating AI tools into legal argument reasoning.
― 5 min read
A new method enhances event coreference resolution for better understanding of text.
― 6 min read
A review of how LLMs handle reasoning tasks and their limitations.
― 7 min read
New evaluation methods aim to improve detection of harmful content online.
― 7 min read
A study on using the MGS dataset to identify AI-generated stereotypes.
― 7 min read
A new method enhances on-device models for efficient AI function calling.
― 8 min read
Exploring how IoS could transform our digital experiences by engaging all senses.
― 10 min read
A structured way to assess language models in multilingual contexts.
― 5 min read
Examining the use-mention distinction in speech online.
― 6 min read
This paper examines the ethical challenges of AI in mental health care.
― 5 min read
Kallaama creates a speech dataset in local languages to aid Senegalese farmers.
― 4 min read
This paper discusses how language models learn and evolve through interaction.
― 9 min read
Research highlights how ML and NLP can aid in identifying depression.
― 7 min read
This article examines how language models handle pronouns and the implications for identity.
― 4 min read
Integrating human reasoning into AI training enhances model explanations and builds trust.
― 6 min read
Research shows how curiosity helps robots learn about objects through exploration.
― 7 min read
Combining language and navigation improves how robots function in various environments.
― 7 min read
Addressing content moderation issues in the fediverse with innovative strategies.
― 6 min read