mlsanityData to 7 Oct 2026

Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

arXiv 2212.09736 ↗First posted 19 Dec 2022cs.CL cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

A key missing capacity of current language models (LMs) is grounding to real-world environments. Most existing work for grounded language understanding uses LMs to directly generate plans that can be executed in the environment to achieve the desired effects. It thereby casts the burden of ensuring grammaticality, faithfulness, and controllability all on the LMs. We propose Pangu, a generic framework for grounded language understanding that capitalizes on the discriminative ability of LMs instead of their generative ability. Pangu consists of a symbolic agent and a neural LM working in a concerted fashion: The agent explores the environment to incrementally construct valid plans, and the LM evaluates the plausibility of the candidate plans to guide the search process. A case study on the challenging problem of knowledge base question answering (KBQA), which features a massive environment, demonstrates the remarkable effectiveness and flexibility of Pangu: A BERT-base LM is sufficient for setting a new record on standard KBQA datasets, and larger LMs further bring substantial gains. Pangu also enables, for the first time, effective few-shot in-context learning for KBQA with large LMs such as Codex.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 60 of its 92 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

60 of 92 references.

References · 60

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  7. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  9. 2021Program Synthesis with Large Language Modelscited by 3,509
  10. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  11. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  12. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
38 more
  1. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  2. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  3. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  4. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  6. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  7. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  8. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  9. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  10. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  11. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  12. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  13. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  14. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  15. 2022Binding Language Models in Symbolic Languagescited by 224
  16. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  17. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  18. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  19. 2021Episodic Transformer for Vision-and-Language Navigationcited by 155
  20. 2020Deep Learning Based Text Classification: A Comprehensive Reviewcited by 140
  21. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  22. 2020Task-Oriented Dialogue as Dataflow Synthesiscited by 122
  23. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  24. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  25. 2021Jigsaw: Large Language Models meet Program Synthesiscited by 103
  26. 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 101
  27. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  28. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  29. 2021A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Executioncited by 91
  30. 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
  31. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  32. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  33. 2020Efficient One-Pass End-to-End Entity Linking for Questionscited by 76
  34. 2022Enabling Conversational Interaction with Mobile UI using Large Language Modelscited by 66
  35. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  36. 2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
  37. 2020SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Basescited by 47
  38. 2017Learning to Paraphrase for Question Answeringcited by 46

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 25; 2025: 10; 2026: 8.

57 papers.

Sort:

By area:

  1. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  2. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  3. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  4. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  5. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
  6. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  7. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  8. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agentscited by 144
  9. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  10. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 90
  11. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  12. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
38 more
  1. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  2. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  3. 2023FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answeringcited by 51
  4. 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Modelscited by 48
  5. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  6. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoningcited by 44
  7. 2023SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)cited by 42
  8. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  9. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 38
  10. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  11. 2024Security of AI Agentscited by 24
  12. 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Searchcited by 21
  13. 2024Empowering Large Language Model Agents through Action Learningcited by 20
  14. 2024Teaching Models to Balance Resisting and Accepting Persuasioncited by 19
  15. 2023Instructed Language Models with Retrievers Are Powerful Entity Linkerscited by 18
  16. 2024Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agentscited by 17
  17. 2023keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLMcited by 16
  18. 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Mergingcited by 16
  19. 2024Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequencecited by 15
  20. 2024EffiQA: Efficient Question-Answering with Strategic Multi-Model Collaboration on Knowledge Graphscited by 14
  21. 2024Grounding Language Models for Visual Entity Recognitioncited by 12
  22. 2026Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systemscited by 12
  23. 2023Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQAcited by 11
  24. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQAcited by 7
  25. 2024How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answeringcited by 5
  26. 2025Are Autonomous Web Agents Good Testers?cited by 5
  27. 2025Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaborationcited by 4
  28. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4
  29. 2023Data Distribution Bottlenecks in Grounding Language Models to Knowledge Basescited by 3
  30. 2025Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answeringcited by 3
  31. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generationcited by 3
  32. 2025KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answeringcited by 3
  33. 2026Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmarkcited by 3
  34. 2024BERTologyNavigator: Advanced Question Answering with BERT-based Semanticscited by 2
  35. 2025Enhancing Retrieval Systems with Inference-Time Logical Reasoningcited by 2
  36. 2026Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphscited by 2
  37. 2024KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Basescited by 1
  38. 2024Semantic Parsing with Candidate Expressions for Knowledge Base Question Answeringcited by 1

50 most cited of 57 All 57 (JSON)