IP Library › Granted Patent US 12,346,828
Granted Patent B2
US 12,346,828 · App. 18/967,327 · Granted Jul 1, 2025

Image analysis by prompting of machine-learned models using chain of thought

Inventors: Jason Weng Wei (Mountain View, CA); Dengyong Zhou (Redmond, WA); Dale Eric Schuurmans (Edmonton, CA); Quoc V. Le (Sunnyvale, CA); Maarten Paul Bosma (Cupertino, CA); Ed Huai-Hsin Chi (Palo Alto, CA); Olivier Jean Andrè Bousquet (Zürich, CH); Le Hou (South Setauket, NY); Nathan Scales (Mountain View, CA); David J. Bieber (New York, NY); Charles Aloysius Sutton (Santa Clara, CA); Nathanael Schärli (Mountain View, CA); Augustus Quadrozzi Odena (San Francisco, CA); Sharan Narang (Mountain View, CA); Guy Gur-Ari Krakover (Palo Alto, CA); Aakanksha Chowdhery (Santa Clara, CA); Aitor Lewkowycz (Mountain View, CA); Jiageng Luan (San Francisco, CA); David Martin Dohan (San Francisco, CA); Henryk Michalewski (Mountain View, CA); Jacob Austin (New York, NY); Anders Johan Andreassen (Princeton, NJ); Maxwell Nye (Mountain View, CA); Xuezhi Wang (New York, NY)
Assignee: GOOGLE LLC
G06N5/022
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,346,828
App. No.
18/967,327
Filed
Dec 3, 2024
Granted
Jul 1, 2025
Kind
B2
Art Unit
2161
USPC
706/12
Abstract

An example technique for image analysis is provided. An example image analysis method includes obtaining an instructive sequence descriptive of an instructive query, an instructive response, and an instructive trace of intermediate states from the instructive query to the instructive response. The example image analysis method includes inputting, to a machine-learned model, the instructive sequence and an operative image processing query that comprises image data, wherein the machine-learned model is configured to process the operative query with attention over the instructive sequence. The example method can include generating, using the machine-learned model and responsive to the operative query, an operative image processing response that comprises an analysis of the image data.

Claims (42)

1. A computer-implemented method for performing image analysis, the method comprising:

obtaining, by a computing system comprising one or more processors, an instructive sequence descriptive of an instructive query, an instructive response, and an instructive trace of intermediate states from the instructive query to the instructive response;

inputting, by the computing system and to a machine-learned model, the instructive sequence and an operative image processing query comprising image data, wherein the machine-learned model is configured to process the operative image processing query with attention over the instructive sequence; and

generating, by the computing system, using the machine-learned model and responsive to the operative image processing query, an operative image processing response.

2. The computer-implemented method of claim 1 , comprising:

generating, by the computing system, using the machine-learned model and responsive to the operative image processing query, an operative trace of intermediate states from the operative query to the operative image processing response.

3. The computer-implemented method of claim 1 , wherein the instructive sequence is prepended to the operative image processing query.

4. The computer-implemented method of claim 2 , wherein the instructive trace comprises a chain of intermediate responses to intermediate queries.

5. The computer-implemented method of claim 1 , wherein the instructive sequence comprises an input flag and an output flag.

6. The computer-implemented method of claim 1 , wherein the instructive sequence comprises a tokenized representation of a natural language.

7. The computer-implemented method of claim 1 , wherein the instructive trace comprises one or more intermediate states of one or more variables declared by a computer-executable coding language.

8. The computer-implemented method of claim 1 , wherein generating the operative response comprises:

generating, by the computing system and using the machine-learned model, a plurality of operative responses; and

determining, by the computing system, the operative image processing response based on a sample of the plurality of operative responses.

9. The computer-implemented method of claim 8 , wherein determining the operative image processing response comprises:

determining, by the computing system, a consistency metric based on the sample of the plurality of operative responses.

10. The computer-implemented method of claim 8 , wherein the sample is based on respective probabilities associated with the plurality of operative responses.

11. The computer-implemented method of claim 9 , wherein the consistency metric comprises at least one of: a plurality vote, or a majority vote.

12. The computer-implemented method of claim 9 , wherein the consistency metric comprises a vote based on operative responses respectively associated with diverse operative traces.

13. The computer-implemented method of claim 1 , wherein the operative image processing query is a first query component and the operative image processing response is a first response component, and wherein the method comprises:

inputting, by the computing system and to the machine-learned model, the instructive sequence, the first query component, the first response component, and a second query component; and

generating, by the computing system, using the machine-learned model and responsive to the second query component, a second response component.

14. The computer-implemented method of claim 13 , comprising:

generating, by the computing system and responsive to a target query, one or more query components.

15. The computer-implemented method of claim 13 , comprising:

inputting, by the computing system and to the machine-learned model, a preliminary instructive sequence comprising a preliminary instructive query and a preliminary instructive response, wherein the preliminary instructive response comprises a plurality of preliminary instructive query components.

16. The computer-implemented method of claim 13 , wherein the first query component and the second query component are generated with a different machine-learned model other than the machine-learned model used to obtain the first response component and the second response component.

17. The computer-implemented method of claim 14 , wherein the second query component corresponds to the target query.

18. The computer-implemented method of claim 13 , comprising, for a plurality of iterations:

generating, by the computing system, an updated instructive sequence based on combining one or more prior input sequences with one or more output sequences respectively corresponding thereto;

inputting, by the computing system and to the machine-learned model, the updated instructive sequence and an additional query component; and

generating, by the computing system, using the machine-learned model and responsive to the additional query component, an additional response component.

19. One or more memory devices storing non-transitory computer-readable instructions executable to cause one or more processors to perform operations for performing image analysis, the operations comprising:

obtaining an instructive sequence descriptive of an instructive query, an instructive response, and an instructive trace of intermediate states from the instructive query to the instructive response;

inputting, to a machine-learned model, the instructive sequence and an operative image processing query comprising image data, wherein the machine-learned model is configured to process the operative image processing query with attention over the instructive sequence; and

generating, using the machine-learned model and responsive to the operative image processing query, an operative image processing response.

20. A computing system for performing image analysis, the system comprising:

one or more processors; and

one or more memory devices storing non-transitory computer-readable instructions that are executable to cause the one or more processors to perform operations, the operations comprising:

obtaining an instructive sequence descriptive of an instructive query, an instructive response, and an instructive trace of intermediate states from the instructive query to the instructive response;

inputting, to a machine-learned model, the instructive sequence and an operative image processing query comprising image data, wherein the machine-learned model is configured to process the operative image processing query with attention over the instructive sequence; and

generating, using the machine-learned model and responsive to the operative image processing query, an operative image processing response.

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE SPELLING OF ASSIGNORS' NAMES: AITOR LEWKOWYCZ AND JIAGENG LUAN PREVIOUSLY RECORDED AT REEL: 70229 FRAME: 768. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Feb 26, 2025
From: WEI, JASON WENG; ZHOU, DENGYONG; WANG, XUEZHI; SCHUURMANS, DALE ERIC; LE, QUOC V.; BOSMA, MAARTEN PAUL; CHI, ED HUAI-HSIN; BOUSQUET, OLIVIER JEAN ANDRE; HOU, LE; SUTTON, CHARLES ALOYSIUS; SCHARLI, NATHANAEL MARTIN; SCALES, NATHAN KEMP SEKIGUCHI; ODENA, AUGUSTUS QUADROZZI; NARANG, SHARAN AJIT; KRAKOVER, GUY GUR-ARI; CHOWDHERY, AAKANKSHA; DOHAN, DAVID MARTIN; LEWKOWYCZ, AITOR; MICHALEWSKI, HENRYK; LUAN, JIAGENG; BIEBER, DAVID J..; AUSTIN, JACOB; ANDREASSEN, ANDERS JOHAN; NYE, MAXWELL ISAAC
To: GOOGLE LLC
Reel/Frame 070763/0737 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 17, 2025
From: WEI, JASON WENG; ZHOU, DENGYONG; WANG, XUEZHI; SCHUURMANS, DALE ERIC; LE, QUOC V.; BOSMA, MAARTEN PAUL; CHI, ED HUAI-HSIN; BOUSQUET, OLIVIER JEAN ANDRE; HOU, LE; SUTTON, CHARLES ALOYSIUS; SCHARLI, NATHANAEL MARTIN; SCALES, NATHAN KEMP SEKIGUCHI; ODENA, AUGUSTUS QUADROZZI; NARANG, SHARAN NAJIT; KRAKOVER, GUY GUR-ARI; CHOWDHERY, AAKANKSHA; DOHAN, DAVID MARTIN; LEWKOWYCA, AITOR; MICHALEWSKI, HENRYK; LUAN, DAVID; BIEBER, DAVID J.; AUSTIN, JACOB; ANDREASSEN, ANDERS JOHAN; NYE, MAXWELL ISAAC
To: GOOGLE LLC
Reel/Frame 070229/0768 →
Continuity (4)
Continuation PCTUS2023023918 · May 31, 2023
Continuation 17881746 · Aug 5, 2022
Provisional Application 63348637 · Jun 3, 2022
Related Publication 20250094838A1 · Mar 20, 2025
References Cited (90)
US 11574131B2 · Shazeer et al. · 2023 [cited by applicant]
US 11960848B2 · Shazeer et al. · 2024 [cited by applicant]
US 20220374608A1 · Shazeer · 2022 [cited by examiner]
US 20240220734A1 · Shazeer et al. · 2024 [cited by applicant]
US 20240256786A1 · Shazeer et al. · 2024 [cited by applicant]
US 20240303422A1 · Fabian · 2024 [cited by examiner]
Ahn et al, “Do as I Can, Not as I Say: Grounding Language in Robotic Affordances”, arXiv:2204.01691v2, Aug. 16, 2022, 34 pages. [cited by applicant]
Amini et al, “MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms”, arXiv:1905.13319v1, May 30, 2019, 11 pages. [cited by applicant]
Andor et al, “Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension”, arXiv:1909.00109v2, Sep. 12, 2019, 10 pages. [cited by applicant]
Andreas et al, “Learning with Latent Language”, arXiv:1711.00482v1, Nov. 1, 2017, 16 pages. [cited by applicant]
Austin et al, “Program Synthesis with Large Language Models”, arXiv:2108.07732v1, Aug. 16, 2021, 34 pages. [cited by applicant]
Bostrom et al, “Flexible Generation of Natural Language Deductions”, arXiv:2104.08825v2, Sep. 9, 2021, 13 pages. [cited by applicant]
Brown et al, “Language Models are Few-Shot Learners”, arXiv:2005.14165v4, Jul. 22, 2020, 75 pages. [cited by applicant]
Cai et al, “Making Neural Programming Architectures Generalize via Recursion”, arXiv:1704.06611v1, Apr. 21, 2017, 20 pages. [cited by applicant]
Camburu et al, “e-SNLI: Natural Language Inference with Natural Language Explanations”, arXiv:1812.01193v2, Dec. 6, 2018, 13 pages. [cited by applicant]
Chen et al, “Can Rationalization Improve Robustness?”, arXiv:2204.11790v2, May 3, 2022, 14 pages. [cited by applicant]
Chen et al, “Evaluating Large Language Models Trained on Code”, arXiv:2107.03374v2, Jul. 14, 2021, 35 pages. [cited by applicant]
Chen et al, “Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension”, International Conference on Learning Representations, Apr. 26-May 1, 2020, Virtual, 16 pa… [cited by applicant]
Chiang et al, “Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems”, arXiv:1811.00720v2, Jun. 9, 2019, 13 pages. [cited by applicant]
Chowdhery et al, “PaLM: Scaling Language Modeling with Pathways”, arXiv:2204.02311v3, Apr. 19, 2022, 83 pages. [cited by applicant]
Clark et al, “Transformers as Soft Reasoners Over Language”, arXiv:2002.05867v2, May 5, 2020, 15 pages. [cited by applicant]
Cobbe et al, “Training Verifiers to Solve Math Word Problems”, arXiv:2110.14168v2, Nov. 18, 2021, 22 pages. [cited by applicant]
Devlin et al, “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding”, arXiv:1810.04805v2, May 24, 2019, 16 pages. [cited by applicant]
Dong et al, “Neural Logic Machines”, arXiv:1904.11694v1, Apr. 26, 2019, 22 pages. [cited by applicant]
Dua et al, “Benefits of Intermediate Annotations in Reading Comprehension”, Association for Computational Linguistics, Jul. 5-10, 2020, Virtual, pp. 5627-5634. [cited by applicant]
Geva et al, “Did Aristotle use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies”, arXiv:2101.02235v1, Jan. 6, 2021, 15 pages. [cited by applicant]
Gu et al, “DREAM: Uncovering Mental Models Behind Language Models”, arXiv:2112.08656v1, Dec. 16, 2021, 12 pages. [cited by applicant]
Hancock et al, “Training Classifiers with Natural Language Explanations”, arXiv:1805.03818v4, Aug. 25, 2018, 12 pages. [cited by applicant]
Hase et al, “When Can Models Learn from Explanations? A Formal Framework for Understanding the Roles of Explanation Data”, arXiv:2102.02201v2, Feb. 10, 2021, 25 pages. [cited by applicant]
Hendrycks et al, “Measuring Mathematical Problem Solving with the Math Dataset”, arXiv:2103.03874v2, Nov. 8, 2021, 22 pages. [cited by applicant]
Hosseini et al, 2014. Learning to Solve Arithmetic Word Problems with Verb Categorization, Conference on Empirical Methods in Natural Language Processing, Oct. 25-29, 2014, Doha, Qatar, 11 pages. [cited by applicant]
International Preliminary Report on Patentability for PCT/US2023/023918, mailed on Dec. 12, 2024, 11 pages. [cited by applicant]
International Search Report and Written Opinion for Application No. PCT/US2023/023918, mailed Aug. 2, 2023, 16 pages. [cited by applicant]
Jie et al, “Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction”, arXiv:2203.10316v3, Apr. 25, 2022, 12 pages. [cited by applicant]
Kaplan et al, “Scaling Laws for Neural Language Models”, arXiv:2001.08361v1, Jan. 23, 2020, 30 pages. [cited by applicant]
Koncel-Kedziorski et al, “Mawps: A Math Word Problem Repository”, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun. 12-17, 2016, San Diego, Cali… [cited by applicant]
Lampinen et al, “Can Language Models Learn from Explanations in Context?”, arXiv:2204.02329v3, May 20, 2022, 29 pages. [cited by applicant]
Lan et al, “MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers”, arXiv:2109.00799v2, Sep. 18, 2021, 9 pages. [cited by applicant]
Lester et al, “The Power of Scale for Parameter-Efficient Prompt Tuning”, arXiv:2104.08691v2, Sep. 2, 2021, 15 pages. [cited by applicant]
Lev et al, “Solving Logic Puzzles: From Robust Processing to Precise Semantics”, Workshop on Text Meaning and Interpretation, Jul. 2004, Barcelona, Spain, 8 pages. [cited by applicant]
Li et al, “Prefix-Tuning: Optimizing Continuous Prompts for Generation”, arXiv:2101.00190v1, Jan. 1, 2021, 15 pages. [cited by applicant]
Liang et al, “Explainable Multi-Hop Verbal Reasoning Through Internal Monologue”, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun. 2021, Virtua… [cited by applicant]
Ling et al, “Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems”, ar Xiv: 1705.04146v3, Oct. 23, 2017, 10 pages. [cited by applicant]
Liu et al, “Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing”, arXiv:2107.13586v1, Jul. 28, 2021, 46 pages. [cited by applicant]
Majumder et al, “Rationale-Inspired Natural Language Explanations with Commonsense”, arXiv:2106.13876v3, Jun. 29, 2022, 16 pages. [cited by applicant]
Mao et al, “Grammar-Based Grounded Lexicon Learning”, Conference on Neural Information Processing Systems, Dec. 6-14, 2021, Virtual, 14 pages. [cited by applicant]
Marasovic et al, “Few-Shot Self-Rationalization with Natural Language Prompts”, arXiv:2111.08284v2, Apr. 26, 2022, 15 pages. [cited by applicant]
Min et al, “Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?” arXiv:2202.12837v1, Feb. 25, 2022, 14 pages. [cited by applicant]
Mohammed Saeed et al “RuleBERT: Teaching Soft Rules to Pre-Trained Language Models”, arXiv:2109.13006v1, Sep. 24, 2021, 17 pages. [cited by applicant]
Narang et al, “WT5 ?! Training Text-to-Text Models to Explain Their Predictions”, arXiv:2004.14546v1, Apr. 30, 2020, 16 pages. [cited by applicant]
Nye et al, “Show your Work: Scratchpads for Intermediate Computation with Language Models”, arXiv:2112.00114v1, Nov. 30, 2021,16 pages. [cited by applicant]
Ouyang et al, “Training Language Models to Follow Instructions with Human Feedback”, arXiv:2203.02155v1, Mar. 4, 2022, 68 pages. [cited by applicant]
Patel et al, “Are NLP Models Really Able to Solve Simple Math Word Problems?”, arXiv:2103.07191v2, Apr. 15, 2021, 16 pages. [cited by applicant]
Peters et al, “Deep Contextualized Word Representations”, arXiv:1802.05365v2, Mar. 22, 2018, 15 pages. [cited by applicant]
Pi et al, “Reasoning like Program Executors”, arXiv:2201.11473v1, Jan. 27, 2022, 17 pages. [cited by applicant]
Piekos et al, “Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning”, arXiv:2106.03921v1, Jun. 7, 2021, 13 pages. [cited by applicant]
Rae et al, “Scaling Language Models: Methods, Analysis & Insights from Training Gopher”, arXiv:2112.11446v2, Jan. 21, 2022, 120 pages. [cited by applicant]
Raffel et al, “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer”, arXiv:1910.10683v3, Jul. 28, 2020, 67 pages. [cited by applicant]
Rajagopal et al, “SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers”, arXiv:2103.12279v2, Sep. 8, 2021, 16 pages. [cited by applicant]
Rajanin et al, Explain Yourself! Leveraging Language Models for Commonsense Reasoning, arXiv: 1906.02361v1, Jun. 6, 2019, 11 pages. [cited by applicant]
Ran et al, “NumNet: Machine Reading Comprehension with Numerical Reasoning”, arXiv:1910.06701v1, Oct. 15, 2019, 11 pages. [cited by applicant]
Recchia, “Teaching Autoregressive Language Models Complex Tasks by Demonstration”, arXiv:2109.02102v1, Dec. 3, 2021, 15 pages. [cited by applicant]
Reif et al, “A Recipe for Arbitrary Text Style Transfer with Large Language Models”, arXiv:2109.03910v4, Mar. 31, 2022, 12 pages. [cited by applicant]
Reynolds et al, “Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm”, arXiv:2102.07350v1, Feb. 15, 2021, 10 pages. [cited by applicant]
Roy et al, “Solving General Arithmetic Word Problems”, arXiv:1608.01413v2, Aug. 20, 2016, 10 pages. [cited by applicant]
Sanh et al, “Multitask Prompted Training Enables Zero-Shot Task Generalization”, arXiv:2110.08207v3, Mar. 17, 2022, 216 pages. [cited by applicant]
Scao et al, “How Many Data Points is a Prompt Worth?” arXiv:2103.08493v2, Apr. 6, 2021, 10 pages. [cited by applicant]
Shen Yun Miao, Chao Chun Liang, and Keh Yih Su. 2020. A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers, Association for Computational Linguistics, Jul. 5-10, 2020, Virtual, pp. 975-984. [cited by applicant]
Srivastava et al, “Beyond the Imitation Game: Measuring and Extrapolating the Capabilities of Language Models”, arXiv:2206.04615v2, Jun. 10, 2022, 100 pages. [cited by applicant]
Talmor et al, “CommonsenseQA 2.0: Exposing the Limits of AI through Gamification”, arXiv:2201.05320v1, Jan. 14, 2022, 14 pages. [cited by applicant]
Talmor et al, “CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge”, arXiv:1811.00937v2, Mar. 15, 2019, 10 pages. [cited by applicant]
Talmor et al, “Leap-of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge”, arXiv:2006.06609v3, Nov. 14, 2020, 13 pages. [cited by applicant]
Thoppilan et al, “LaMDA: Language Models for Dialog Applications”, arXiv:2201.08239v3, Feb. 10, 2022, 47 pages. [cited by applicant]
Wang et al, “Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks”, arXiv:2204.07705v2, Apr. 29, 2022, 22 pages. [cited by applicant]
Wang et al, “Self-Consistency Improves Chain of Thought Reasoning in Language Models”, arXiv:2203.11171v2, Apr. 6, 2022, 18 pages. [cited by applicant]
Wei et al, “Finetuned Language Models are Zero-Shot Learners”, arXiv:2109.01652v5, Feb. 8, 2022, 46 pages. [cited by applicant]
Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models”, Thirty-Sixth International Conference on Neural Information Processing Systems, New Orleans, Louisiana, United States, Nov. 28-Dec. 9.… [cited by applicant]
Wiegreffe et al, “Measuring Association Between Labels and Free-Text Rationales”, Conference on Empirical Methods in Natural Language Processing, Nov. 2021, Virtual, pp. 10266-10284. [cited by applicant]
Wiegreffe et al, “Teach Me to Explain: A Review of Datasets for Explainable NLP”, arXiv:2102.12060v4, Dec. 7, 2021, 29 pages. [cited by applicant]
Wiegreffe, “Reframing Human-AI Collaboration for Generating Free-Text Explanations”, arXiv:2112.08674v2, May 4, 2022, 27 pages. [cited by applicant]
Wu et al, “AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts”, arXiv:2110.01691v3, Mar. 17, 2022, 22 pages. [cited by applicant]
Wu et al, “PromptChainer: Chaining Large Language Model Prompts through Visual Programming”, arXiv:2203.06566v1, Mar. 13, 2022, 10 pages. [cited by applicant]
Yan et al, “Neural Execution Engines: Learning to Execute Subroutines”, arXiv:2006.08084v3, Oct. 22, 2020, 21 pages. [cited by applicant]
Yao et al, “Refining Language Models with Compositional Explanations”, arXiv:2103.10415v3, Dec. 31, 2021, 19 pages. [cited by applicant]
Yordanov et al, “Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations”, arXiv:2112.06204v1, Dec. 12, 2021, 20 pages. [cited by applicant]
Zaidan et al, “Using “Annotator Rationales” to Improve Machine Learning for Text Categorization”, Conference of the North American Chapter of the Association for Computational Linguistics, Apr. 2007, Rochester, New York… [cited by applicant]
Zaremba et al, “Learning to Execute”, arXiv:1410.4615v3. Feb. 19, 2015. 25 pages. [cited by applicant]
Zelikman et al, “STaR: Bootstrapping Reasoning with Reasoning”, arXiv:2203.14465v2, May 20, 2022, 30 pages. [cited by applicant]
Zhao et al, “Calibrate Before Use: Improving Few-Shot Performance of Language Models”, arXiv:2102.09690v2, Jun. 10, 2021, 15 pages. [cited by applicant]
Zhou et al, “Towards Interpretable Natural Language Understanding with Explanations as Latent Variables”, arXiv:2011.05268v3, May 26, 2022, 16 pages. [cited by applicant]
Cited By (2)
US 12,585,880 US 12,737,648