MikeLabs
Tag

llm

#llm

More content

Read more stories on Hashnode

Articles with this tag

LLMs will lie forever

Sep 25, 20245 min read

Hallucinations are never going away. How can we reduce them? · Can we ever really trust AI? As LLMs become more advanced, they still face a major issue:...

LLMs will lie forever

LLMs are secretly good at regression calculations

Apr 13, 202410 min read

If you know the special way to prompt them, that is. · “Figure 7: The cumulative regret of two large language models on two different non-linear...

How to improve your semantic search with hypothetical document embeddings

Mar 28, 202411 min read

How to use a simple LLM call to dramatically improve the quality of your semantic search results · Finding the right AI model to build a workflow around...

Researchers: Low-Resource Languages Can Easily Jailbreak LLMs

Oct 8, 20234 min read

These results clearly demonstrate safety mechanisms do not properly generalize across languages · Recent advances in artificial intelligence LLMs have...

Researchers: Low-Resource Languages Can Easily Jailbreak LLMs

Enabling Language Models to Implicitly Learn Self-Improvement

Oct 6, 20235 min read

Rather than manually distilling criteria into prompts, implicit information in preference data can be leveraged. · Recent years have seen remarkable...

Enabling Language Models to Implicitly Learn Self-Improvement

Tool-Integrated Reasoning: A New Approach for Math-Savvy LLMs

Oct 3, 20235 min read

TORA combines both rationale-based and program-based reasoning to deliver results to math problems that were previously too difficult for LLMs to solv ·...

Tool-Integrated Reasoning: A New Approach for Math-Savvy LLMs