Zain Hasan sur X : "why do large language models pay more attention to and reason better over the beginning and end of what you tell them in prompts?"
Tags:
About This Document
File info
Documents with similar tags (experimental)
Aran Komatsuzaki sur X : "performance of LLMs with user prompt at the top vs. bottom of the user input (e.g. this image)"
Tags:
2024-03-31 About
GitHub - microsoft/LLMLingua: To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Tags:
2024-01-18 About
LlamaIndex 🦙 (GPT Index) sur Twitter : "Pretty much everyone building LLM apps over data has to figure out how to... cram arbitrary data into limited context windows?"
Tags:
2023-07-09 About
Archit Sharma sur Twitter : "Direct Preference Optimization (DPO) allows you to fine-tune LMs directly from preferences via a simple classification loss, no RL required"
Tags:
2023-05-31 About
Eric sur Twitter : "...Introducing Direct Preference Optimization (DPO), a simple classification loss provably equivalent to RLHF"
Tags:
2023-05-31 About
Aran Komatsuzaki sur Twitter : "Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory System Enables LLMs to outperform ChatGPT in scenarios involving ultra-long document summarization or long-term conversations."
Tags:
2023-04-27 About
Aran Komatsuzaki sur Twitter : "Scaling Transformer to 1M tokens and beyond with Recurrent Memory Transformer..."
Tags:
2023-04-25 About
The Rundown AI sur Twitter : "... useful ChatGPT prompt techniques ..."
Tags:
2023-04-20 About
shikhar sur Twitter : "Instead of asking whether tree structure should be baked into NNs, our new paper asks if transformers already have a tendency to learn tree structured computations when trained on language, and if this structure is predictive of generalization! "
Tags:
2022-12-09 About
Stanford NLP Group sur Twitter : "YONO: You Only Need One Model for Open-domain Question Answering..."
Tags:
2022-12-05 About
Stanford NLP Group sur Twitter : "...how to use AI systems to augment the work of humans in interactive systems "
Tags:
2022-03-05 About
AK sur Twitter : "You Only Need One Model for Open-domain Question Answering..."
Tags:
2021-12-23 About
Seth Stafford sur Twitter : "Here’s a nice paper (ICLR spotlight) on how to apply masking in LM training..."
Tags:
2021-10-16 About