🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

Mixture of In-Context Learners Uses subsets of demonstrations to train experts via in-context learning. Given a training set, a trainable weighting function is used to combine the experts' next-token predictions. This approach applies to black-box LLMs since access to the internal parameters of the LLM is not required. Good properties include the following: - competitive with standard ICL while being significantly more data, memory, and computationally efficient - resilient to noisy demonstrations and label imbalance Overall, it is a very cool and simple approach to make better use of in-context demonstrations which is one of the more important methods to get the most out of the LLMs today.

View on Twitter

🔧 Raw API Response

{
  "user": {
    "created_at": "2015-09-04T12:59:26.000Z",
    "default_profile_image": false,
    "description": "Building with AI Agents @dair_ai • Prev: Meta AI, Elastic, Galactica LLM, PhD • I also teach how to build with LLMs, RAG & AI Agents ⬇️",
    "fast_followers_count": 0,
    "favourites_count": 27933,
    "followers_count": 216712,
    "friends_count": 532,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 3688,
    "location": "",
    "media_count": 2656,
    "name": "elvis",
    "normal_followers_count": 216712,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "screen_name": "omarsar0",
    "statuses_count": 12439,
    "translator_type": "regular",
    "url": "https://t.co/JBU5beHQNs",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "3448284313"
  },
  "id": "1854252169492562171",
  "conversation_id": "1854252169492562171",
  "full_text": "Mixture of In-Context Learners\n\nUses subsets of demonstrations to train experts via in-context learning. Given a training set, a trainable weighting function is used to combine the experts' next-token predictions.\n\nThis approach applies to black-box LLMs since access to the internal parameters of the LLM is not required.\n\nGood properties include the following:\n- competitive with standard ICL while being significantly more data, memory, and computationally efficient\n- resilient to noisy demonstrations and label imbalance\n\nOverall, it is a very cool and simple approach to make better use of in-context demonstrations which is one of the more important methods to get the most out of the LLMs today.",
  "reply_count": 5,
  "retweet_count": 78,
  "favorite_count": 318,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GbughQsaIAAyC7e.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/omarsar0/status/1854252169492562171",
  "created_at": "2024-11-06T19:59:02.000Z",
  "#sort_index": "1854252169492562171",
  "view_count": 27977,
  "quote_count": 2,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/omarsar0/status/1854252169492562171"
}