Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-004-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-004-alpha.b-cdn.net
      • sl-yoda-v2-stream-004-beta.b-cdn.net
      • 1685195716.rsc.cdn77.org
      • 1239898752.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems

            Dec 2, 2022

            Speakers

            FZ

            Fan Zhou

            Speaker · 0 followers

            HD

            Haoyu Dong

            Speaker · 0 followers

            QL

            Qian Liu

            Speaker · 1 follower

            About

            Recent language models have struggled to generalize to a large range of numbers in numerical reasoning.In this paper, we propose a novel method that leverages simple numbers as anchors to characterize the implicitly inferred arithmetic expressions from language models, and then explicitly applies the expressions to original numbers to get the answers.Experimental results on several numerical reasoning benchmarks demonstrate that our approach is highly effective.More importantly, our approach wor…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 952 followers

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Sepsis Differential Care by  Identifying the Intent of Expert
            03:12

            Sepsis Differential Care by Identifying the Intent of Expert

            Hyewon Jeong, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Peer Prediction for Learning Agents
            00:57

            Peer Prediction for Learning Agents

            Shi Feng, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%

            [Re] Explaining in Style: Training a GAN to explain a classifier in StyleSpace
            04:33

            [Re] Explaining in Style: Training a GAN to explain a classifier in StyleSpace

            Chase Van De Geijn, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Joint Entropy Search For Maximally-Informed Bayesian Optimization
            05:03

            Joint Entropy Search For Maximally-Informed Bayesian Optimization

            Carl Hvarfner, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Explaining a Reinforcement Learning Agent via Prototyping
            05:04

            Explaining a Reinforcement Learning Agent via Prototyping

            Ronilo Ragodos, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning
            04:57

            ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning

            Eddy Hudson, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow NeurIPS 2022