mlsanityData to 14 Oct 2026

Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledge

arXiv 2509.08808 ↗First posted 10 Sep 2025cs.SEcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

We study the problem of Open-Vocabulary Constructs(OVCs) -- ones not known beforehand -- in the context of converting natural language (NL) specifications into formal languages (e.g., temporal logic or code). Models fare poorly on OVCs due to a lack of necessary knowledge a priori. In such situations, a domain expert can provide correct constructs at inference time based on their preferences or domain knowledge. Our goal is to effectively reuse this inference-time, expert-provided knowledge for future parses without retraining the model. We present dynamic knowledge-augmented parsing(DKAP), where in addition to the input sentence, the model receives (dynamically growing) expert knowledge as a key-value lexicon that associates NL phrases with correct OVC constructs. We propose ROLex, a retrieval-augmented parsing approach that uses this lexicon. A retriever and a generator are trained to find and use the key-value store to produce the correct parse. A key challenge lies in curating data for this retrieval-augmented parser. We utilize synthetic data generation and the data augmentation techniques on annotated (NL sentence, FL statement) pairs to train the augmented parser. To improve training effectiveness, we propose multiple strategies to teach models to focus on the relevant subset of retrieved knowledge. Finally, we introduce a new evaluation paradigm modeled after the DKAP problem and simulate the scenario across three formalization tasks (NL2LTL, NL2Code, and NL2CMD). Our evaluations show that DKAP is a difficult challenge, and ROLex helps improve the performance of baseline models by using dynamic expert knowledge effectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 37 of its 48 references that are in the map. First posted on arXiv 10 Sep 2025.

Builds on

37 of 48 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing25 Oct
  2. 2021RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing21 Sep
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 34

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  7. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  8. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  9. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  10. 2022Autoformalization with Large Language Modelscited by 263
  11. 2017Efficient Natural Language Response Suggestion for Smart Replycited by 229
  12. 2018Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflowcited by 165
22 more
  1. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  2. 2021Retrieval Augmented Code Generation and Summarizationcited by 149
  3. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
  4. 2016Data Recombination for Neural Semantic Parsingcited by 111
  5. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  6. 2020CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characterscited by 87
  7. 2016DeepMath - Deep Sequence Models for Premise Selectioncited by 81
  8. 2020Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsingcited by 72
  9. 2023NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Modelscited by 59
  10. 2020Teaching Temporal Logics to Neural Networkscited by 51
  11. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  12. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  13. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  14. 2020Compositional Generalization via Semantic Taggingcited by 32
  15. 2021DeepSTL -- From English Requirements to Signal Temporal Logiccited by 22
  16. 2020Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answeringcited by 16
  17. 2022Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsingcited by 15
  18. 2022Open Vocabulary Extreme Classification Using Generative Modelscited by 13
  19. 2022Open-Vocabulary Argument Role Prediction for Event Extractioncited by 11
  20. 2017Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modelingcited by 8
  21. 2022ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Modelscited by 6
  22. 2016Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledgecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge
  2. 2024Retrieval is Accurate Generation
  3. 2026Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
  4. 2019Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study
  5. 2024Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models
  6. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey
  7. 2023Dynamic Retrieval-Augmented Generation
  8. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation