🐦 Twitter Post Details

Viewing enriched Twitter post

@iScienceLuvr

Reverse Thinking Makes LLMs Stronger Reasoners abs: https://t.co/s2gcACjUGm "Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as it enables consistency checks between their forward and backward thinking." Train an LLM to be able to generate forward reasoning from question, backward question, and backward reaoning from backward question Shows an average 13.53% improvement over the student model’s zero-shot performance

View on Twitter

📊 Media Metadata

{
  "data": [
    {
      "id": "",
      "type": "photo",
      "url": null,
      "media_url": "https://pbs.twimg.com/media/GdyUJJyXQAAu5AS.jpg",
      "media_url_https": null,
      "display_url": null,
      "expanded_url": null
    }
  ],
  "score": 0.86,
  "scored_at": "2025-08-09T13:46:07.555466",
  "import_source": "network_archive_import",
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1863527576687268241/media_0.jpg?",
      "filename": "media_0.jpg",
      "original_url": "https://pbs.twimg.com/media/GdyUJJyXQAAu5AS.jpg"
    }
  ],
  "storage_migrated": true
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2011-12-20T03:45:50.000Z",
    "default_profile_image": false,
    "description": "PhD at 19 |\nFounder and CEO at @MedARC_AI |\nResearch Director at @StabilityAI | \n@kaggle Notebooks GM |\nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/xPxwKTpz0D",
    "fast_followers_count": 0,
    "favourites_count": 83822,
    "followers_count": 63881,
    "friends_count": 1100,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 974,
    "location": "",
    "media_count": 1828,
    "name": "Tanishq Mathew Abraham, Ph.D.",
    "normal_followers_count": 63881,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1675968078",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1553508977735962624/nnlSwBmu_normal.jpg",
    "screen_name": "iScienceLuvr",
    "statuses_count": 14515,
    "translator_type": "none",
    "url": "https://t.co/nNzCz2VVd1",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "441465751"
  },
  "id": "1863527576687268241",
  "conversation_id": "1863527576687268241",
  "full_text": "Reverse Thinking Makes LLMs Stronger Reasoners\n\nabs: https://t.co/s2gcACjUGm\n\n\"Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as it enables consistency checks between their forward and backward thinking.\"\n\nTrain an LLM to be able to generate forward reasoning from question, backward question, and backward reaoning from backward question\n\nShows an average 13.53% improvement over the student model’s zero-shot performance",
  "reply_count": 17,
  "retweet_count": 153,
  "favorite_count": 770,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [
    {
      "url": "https://t.co/pGevBHjEeb",
      "expanded_url": "https://arxiv.org/abs/2411.19865",
      "display_url": "arxiv.org/abs/2411.19865"
    }
  ],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GdyUJJyXQAAu5AS.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/iScienceLuvr/status/1863527576687268241",
  "created_at": "2024-12-02T10:16:11.000Z",
  "#sort_index": "1863527576687268241",
  "view_count": 55700,
  "quote_count": 8,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/iscienceluvr/status/1863527576687268241"
}