Learning to Plan Long-Term for Language Modeling
Not on the map. Why?
Abstract (arXiv)
Modern language models predict the next token in the sequence by considering the past text through a powerful function such as attention. However, language models have no explicit mechanism that allows them to spend computation time for planning long-distance future text, leading to a suboptimal token prediction. In this paper, we propose a planner that predicts a latent plan for many sentences into the future. By sampling multiple plans at once, we condition the language model on an accurate approximation of the distribution of text continuations, which leads to better next token prediction accuracy. In effect, this allows trading computation time for prediction accuracy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 23 Aug 2024.
Builds on
23 of 42 references.
References · 23
- 2017Attention Is All You Needcited by 60,361
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
- 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
- 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
- 2018Universal Transformerscited by 647
- 2024OLMo: Accelerating the Science of Language Modelscited by 613
11 more
- 2021Datasets: A Community Library for Natural Language Processingcited by 530
- 2016Adaptive Computation Time for Recurrent Neural Networkscited by 506
- 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
- 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 301
- 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 264
- 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 160
- 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
- 2018Learning Longer-term Dependencies in RNNs with Auxiliary Lossescited by 58
- 2024Learning to Plan for Language Modeling from Unlabeled Datacited by 12
- 2021Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representationscited by 5
- 2021Predictive Representation Learning for Language Modelingcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.