Hacker NewsJul 12, 2024
Reasoning skills of large language models are often overestimated
https://news.mit.edu/2024/reasoning-skills-large-language-models-often-overestimated-0711
#ycombinator #MIT_CSAIL #MIT_IBM_Watson_AI_Lab #MIT_Quest_for_Intelligence #large_language_models_LLMs #computer_reasoning #abstract_task_solving #Counterfactual_tasks #general_AI #Zhaofeng_Wu #Yoon_Kim #Jacob_Andreas
Reasoning skills of large language models are often overestimated

MIT CSAIL researchers developed an evaluation framework for large language models about counterfactual tasks. They found that LLMs can recite answers, but struggle to reason as it relates to abstract task-solving.

MIT News | Massachusetts Institute of Technology
 Hacker NewsMar 28, 2024
LLMs use a surprisingly simple mechanism to retrieve some stored knowledge
https://news.mit.edu/2024/large-language-models-use-surprisingly-simple-mechanism-retrieve-stored-knowledge-0325
#ycombinator #Evan_Hernandez #Jacob_Andreas #large_language_models #LLMs #ChatGPT #AI_Interpretability
Large language models use a surprisingly simple mechanism to retrieve some stored knowledge

Researchers find large language models use a simple mechanism to retrieve stored knowledge when they respond to a user prompt. These mechanisms can be leveraged to see what the model knows about different subjects and possibly to correct false information it has stored.

MIT News | Massachusetts Institute of Technology