mlsanityData to 13 Oct 2026

Language Models are Few-Shot Butlers

arXiv 2104.07972 ↗First posted 16 Apr 2021cs.CL cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2% of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51% absolute improvement in success rate over existing methods in the ALFWorld environment.

Key facts. Cited by 27 papers in the map (data through 13 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

20 of 29 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2020Language Models are Few-Shot Learnerscited by 32,320
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  5. 2020Scaling Laws for Neural Language Modelscited by 6,494
  6. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,880
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,215
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,725
  9. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,546
  10. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,376
  11. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  12. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,167
8 more
  1. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 775
  2. 2018CoQA: A Conversational Question Answering Challengecited by 681
  3. 2018TextWorld: A Learning Environment for Text-based Gamescited by 306
  4. 2019Interactive Fiction Games: A Colossal Adventurecited by 166
  5. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  6. 2020Keep CALM and Explore: Language Models for Action Generation in Text-based Gamescited by 108
  7. 2015Deep Reinforcement Learning with a Natural Language Action Spacecited by 88
  8. 2019HIGhER : Improving instruction following with Hindsight Generation for Experience Replaycited by 13

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 6; 2023: 10; 2024: 5; 2025: 5.

27 papers.

Sort:

By area:

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,502
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,065
  3. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 739
  4. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 461
  5. 2023SmartPlay: A Benchmark for LLMs as Intelligent Agentscited by 124
  6. 2023Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorldcited by 65
  7. 2022TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twittercited by 44
  8. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  9. 2022MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learnedcited by 26
  10. 2024WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agentscited by 24
  11. 2022Few-shot Subgoal Planning with Language Modelscited by 22
  12. 2024ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomycited by 22
15 more
  1. 2023Adapting LLM Agents with Universal Feedback in Communicationcited by 19
  2. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17
  3. 2024Policy Improvement using Language Feedback Modelscited by 16
  4. 2023Responsible Task Automation: Empowering Large Language Models as Responsible Task Automatorscited by 14
  5. 2025Generalizability of Large Language Model-Based Agents: A Comprehensive Surveycited by 10
  6. 2024Embodied CoT Distillation From LLM To Off-the-shelf Agentscited by 9
  7. 2023A Picture is Worth a Thousand Words: Language Models Plan from Pixelscited by 6
  8. 2025WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agentscited by 5
  9. 2025EMAC+: Embodied Multimodal Agent for Collaborative Planning with VLM+LLMcited by 5
  10. 2025NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoningcited by 5
  11. 2023Improving Generalization in Task-oriented Dialogues with Workflows and Action Planscited by 3
  12. 2023Code Models are Zero-shot Precondition Reasonerscited by 3
  13. 2024ITCMA: A Generative Agent Based on a Computational Consciousness Structurecited by 3
  14. 2025MCTS-EP: Empowering Embodied Planning with Online Preference Optimizationcited by 2
  15. 2023LLM Guided Inductive Inference for Solving Compositional Problemscited by 0