AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

A Non-monotonic Self-terminating Language Model

Eugene Choi, Kyunghyun Cho, Cheolhyoung Lee

ICLR 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Search for program synthesis · 0 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace vanilla softmax with NMST parametrizationRNN and LSTM · WikiText-2, greedy searchnon-termination ratioImproved
Replace ST parametrization with NMST parametrizationRNN · WikiText-2 validationperplexity: 180.4\pm(3.3) -> 177.4\pm(4.5)Improved
Replace ST parametrization with NMST parametrizationLSTM · WikiText-2 validationperplexity: 104.5\pm(1.4) -> 101.5\pm(0.8)Improved
Use NMST parametrization with ε=1.0×10^-5 instead of vanilla softmaxRNN · WikiText-2 validationperplexity: 178.6\pm(6.3) -> 177.4\pm(4.5)No clear effect
Use NMST parametrization with ε=1.0×10^-5 instead of vanilla softmaxLSTM · WikiText-2 validationperplexity: 101.6\pm(1.0) -> 101.5\pm(0.8)No clear effect
Replace ST parametrization with NMST parametrizationGPT-2 · WikiText-103 validationperplexity: 21.16\pm(0.03) -> 20.69\pm(0.03)Improved
Use NMST parametrization with ε=1.0×10^-5 instead of vanilla softmaxGPT-2 · WikiText-103 validationperplexity: 20.72\pm(0.03) -> 20.69\pm(0.03)No clear effect
Replace vanilla softmax with NMST parametrizationGPT-2 · WikiText-103, greedy search, L=1,000non-termination ratio: 0.27\pm(0.08) -> 0.23\pm(0.10)Improved
Replace ST parametrization with NMST parametrizationGPT-2 · WikiText-103, greedy search, L=1,000non-termination ratio: 0.75\pm(0.10) -> 0.23\pm(0.10)Improved
Replace vanilla softmax with NMST parametrizationGPT-2 · WikiText-103, top-2 sampling, L=1,000non-termination ratio: 0.0\pm(0.0) -> 0.0\pm(0.0)No clear effect
Replace vanilla softmax with NMST parametrizationGPT-2 · WikiText-103, nucleus-0.2 sampling, L=1,000non-termination ratio: 0.25\pm(0.08) -> 0.21\pm(0.10)Improved
Replace vanilla softmax with NMST parametrizationGPT-2 · WikiText-103, nucleus-0.4 sampling, L=1,000non-termination ratio: 0.14\pm(0.05) -> 0.10\pm(0.06)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy