Tag: AI language models
Browse our exclusive articles!
Text Uncanny Valley: LLM Performance Drop on Corrupted Text
Explore how Large Language Models face non-linear performance drops with corrupted text, revealing the Text Uncanny Valley effect in information retrieval.
GSM-SEM: Robust Framework for Semantic Benchmark Variants
Discover GSM-SEM, a framework generating semantically diverse benchmark variants to improve AI model evaluation and reduce memorization bias.
AgentEscapeBench: Benchmarking Tool-Grounded Reasoning in LLMs
Discover how AgentEscapeBench evaluates LLM agents' reasoning with external tools in complex, out-of-domain tasks, highlighting key challenges and insights...
Self-Programmed Execution for Autonomous Language Agents
Discover how self-programmed execution enables language-model agents to operate autonomously with flexible, self-editing code using the Spell language.
When Do Language Models Commit? Finite-Answer Theory
Explore when language models commit to answers with finite-answer theory, revealing key insights into AI decision-making and response stabilization.