AI Studio may get a Grounding adjustment feature for web search
LLMS
-
Google AI Studio May Add YouTube URL Context Support
By
–
AI Studio may get YouTube input context support. Users will be able to upload a YouTube URL along with other files
-
Clarifying LLM token counting behavior
By
–
I agree and I clarify below I’m only claiming to disprove the (common I think) misunderstanding that LLMs normally do count tokens well, just not letters as a special case
-
Training Language Models to Self-Correct via Reinforcement Learning
By
–
Training Language Models to Self-Correct via Reinforcement Learning discuss: https://
huggingface.co/papers/2409.12
917
… Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Existing -
Oryx MLLM: Spatial-Temporal Understanding at Arbitrary Resolution
By
–
Oryx MLLM On-Demand Spatial-Temporal Understanding at Arbitrary Resolution discuss: https://
huggingface.co/papers/2409.12
961
… Visual data comes in various forms, ranging from small icons of just a few pixels to long videos spanning hours. Existing multi-modal LLMs usually standardize these -
On LLM tokenization and misgeneralization
By
–
Some people do take “LLMs see tokens not letters” at face value — i.e. the mental model is LLMs can of course count repetitions of a *token*, but a naive tokenizer makes letters an unnecessarily difficult task. Misgeneralization during training is different and more plausible.
-
InfiMM-WebMath-40B: Advancing Multimodal Mathematical Reasoning
By
–
InfiMM-WebMath-40B Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning discuss: https://
huggingface.co/papers/2409.12
568
… Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in -
Tokenization isn’t the only cause of LLM counting errors
By
–
Many LLM errors *are* downstream of tokenization oddities, surely. But the folk wisdom that two-R’s-in-strawberry mistakes happen *only* because the letters in “strawberry” are combined into longer prompt tokens before the model can count them is demonstrably not true.
-
LLM counting errors: ChatGPT-4o miscounts repeated tokens
By
–
Another clue: LLM counting errors occur even when counting words instead of letters. Here, ChatGPT 4o miscounts just 4 repetitions of “horse” in a 3-line text, despite care to ensure each “horse” maps consistently to the same single token (20998, “horse” with a leading space):
-
Similar responses from o1-mini and Claude 3.5 Sonnet
By
–
Similar responses responses to the same prompt can be seen from o1-mini and Claude 3.5 Sonnet. Other models left as an engagement-bait exercise for the reader.