mlsanityData to 7 Oct 2026

Language Model Cascades

arXiv 2207.10342 ↗First posted 21 Jul 2022cs.CL cs.AIcited by 104

Not on the map. Why?

Cited by 37 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are probabilistic models, and may be expressed in the language of graphical models with random variables whose values are complex data types such as strings. Cases with control flow and dynamic structure require techniques from probabilistic programming, which allow implementing disparate model structures and inference strategies in a unified language. We formalize several existing techniques from this perspective, including scratchpads / chain of thought, verifiers, STaR, selection-inference, and tool use. We refer to the resulting programs as language model cascades.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

22 of 28 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  7. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  8. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  9. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  10. 2019The frontier of simulation-based inferencecited by 490
  11. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 466
  12. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
10 more
  1. 2020Generative Language Modeling for Automated Theorem Provingcited by 379
  2. 2022Self-critiquing models for assisting human evaluatorscited by 372
  3. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  4. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 187
  5. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  6. 2018An Introduction to Probabilistic Programmingcited by 62
  7. 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 61
  8. 2022Training Language Models with Language Feedbackcited by 48
  9. 2016Design and Implementation of Probabilistic Programming Language Anglicancited by 15
  10. 2022Foundation Posteriors for Approximate Probabilistic Inferencecited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 20; 2023: 46; 2024: 15; 2025: 11; 2026: 12.

104 papers.

Sort:

By area:

  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  2. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  3. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  4. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  5. 2022PAL: Program-aided Language Modelscited by 635
  6. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  7. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  8. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  9. 2023Cognitive Architectures for Language Agentscited by 422
  10. 2023Language Models can Solve Computer Taskscited by 371
  11. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  12. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
38 more
  1. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  2. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 270
  3. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  4. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 233
  5. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  6. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
  7. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 158
  8. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  9. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  10. 2023Training Language Models with Language Feedback at Scalecited by 125
  11. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  12. 2023Aligning Language Models with Preferences through f-divergence Minimizationcited by 118
  13. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
  14. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  15. 2023GraphText: Graph Reasoning in Text Spacecited by 110
  16. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 104
  17. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  18. 2023Why think step by step? Reasoning emerges from the locality of experiencecited by 103
  19. 2023STEVE-1: A Generative Model for Text-to-Behavior in Minecraftcited by 95
  20. 2023Amortizing intractable inference in large language modelscited by 94
  21. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  22. 2022PEER: A Collaborative Language Modelcited by 86
  23. 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlocited by 85
  24. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 79
  25. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 77
  26. 2023Eight Things to Know about Large Language Modelscited by 73
  27. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  28. 2023Strategic Reasoning with Language Modelscited by 64
  29. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  30. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  31. 2023Memory Augmented Large Language Models are Computationally Universalcited by 45
  32. 2023LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzlescited by 41
  33. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 36
  34. 2023The Consensus Game: Language Model Generation via Equilibrium Searchcited by 35
  35. 2023What's Left? Concept Grounding with Logic-Enhanced Foundation Modelscited by 33
  36. 2023Joint Prompt Optimization of Stacked LLMs using Variational Inferencecited by 32
  37. 2023Active Preference Inference using Language Models and Probabilistic Reasoningcited by 29
  38. 2022ThinkSum: Probabilistic reasoning over sets using large language modelscited by 23

50 most cited of 104 All 104 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
  2. 2025Reasoning Under Uncertainty: Exploring Probabilistic Reasoning Capabilities of LLMs
  3. 2026Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
  4. 2026What do Language Models Learn and When? The Implicit Curriculum Hypothesis
  5. 2024A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
  6. 2026Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models
  7. 2025A Probabilistic Perspective on Model Collapse
  8. 2026From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models