mlsanityData to 7 Oct 2026

Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

arXiv 2010.15875 ↗First posted 29 Oct 2020cs.AI cs.CLcited by 216

Not on the map. Why?

Cited by 71 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training questions to the test question, meta-learning enables the programmer to adapt to unseen questions to tackle potential distributional biases quickly. However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive. In this paper, we present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision, i.e., the system's performance with respect to the produced answers. To the best of our knowledge, this is the first attempt to train the retrieval model with the programmer jointly. Our system leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases. We have released our code at https://github.com/DevinJake/MARL.

Key facts. Cited by 216 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 28; 2023: 46; 2024: 74; 2025: 51.

216 papers.

Sort:

By area:

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  4. 2021Measuring Coding Challenge Competence With APPScited by 879
  5. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
  6. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
  7. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  8. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  9. 2023A Comprehensive Overview of Large Language Modelscited by 639
  10. 2024OLMo: Accelerating the Science of Language Modelscited by 599
  11. 2023Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningcited by 408
  12. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
38 more
  1. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 233
  2. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  3. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 199
  4. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoningcited by 186
  5. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  6. 2024RegMix: Data Mixture as Regression for Language Model Pre-trainingcited by 172
  7. 2022What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?cited by 149
  8. 2023Chain of Hindsight Aligns Language Models with Feedbackcited by 147
  9. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  10. 2024LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-trainingcited by 122
  11. 2025Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingcited by 116
  12. 2024Language models scale reliably with over-training and on downstream taskscited by 105
  13. 2024MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Modelscited by 96
  14. 2023Cumulative Reasoning with Large Language Modelscited by 94
  15. 2025NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Modelcited by 94
  16. 2022On the Paradox of Learning to Reason from Datacited by 93
  17. 2022What Language Model to Train if You Have One Million GPU Hours?cited by 92
  18. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
  19. 2023DoGE: Domain Reweighting with Generalization Estimationcited by 87
  20. 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examplescited by 84
  21. 2024Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Modelscited by 83
  22. 2024Self-playing Adversarial Language Game Enhances LLM Reasoningcited by 80
  23. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
  24. 2023In-Context Learning with Iterative Demonstration Selectioncited by 74
  25. 2025Efficient Test-Time Scaling via Self-Calibrationcited by 74
  26. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoningcited by 69
  27. 2024LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Modelscited by 67
  28. 2023Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyondcited by 65
  29. 2024Attention Heads of Large Language Models: A Surveycited by 65
  30. 2024Instructional Fingerprinting of Large Language Modelscited by 64
  31. 2024Instruction Pre-Training: Language Models are Supervised Multitask Learnerscited by 63
  32. 2024The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Modelscited by 62
  33. 2023Natural Language Reasoning, A Surveycited by 61
  34. 2023Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translationcited by 59
  35. 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?cited by 56
  36. 2024MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Expertscited by 55
  37. 2025Optimizing Large Language Model Training Using FP4 Quantizationcited by 53
  38. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 52

50 most cited of 216 All 216 (JSON)