Context-Aware Distillation and Ablation for Text2DSL

• URL: http://arxiv.org/abs/2606.22578v1
• Date: Sun, 21 Jun 2026 16:27:24 GMT
• Title: Context-Aware Distillation and Ablation for Text2DSL
• Abstract summary: We replace prompt-only synthetic generation with context-aware distillation.<n>A teacher large language model operates under an explicitly defined structured context.<n>This scales the verified PolkitBench corpus from 4,204 to 10,073 pairs.
• Score: 78.29352305480285
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We extend our prior work on Text2DSL automatic generation of domain-specific language (DSL) code from natural language descriptions along two complementary axes. First, we replace prompt-only synthetic generation with context-aware distillation, in which a teacher large language model (DeepSeek-V4-Flash) operates under an explicitly defined structured context comprising a BNF grammar, an API specification, and a closed identifier vocabulary; the resulting corpus is verified by a two-tier pipeline combining AST validation through esprima and runtime acceptance through the production polkitd daemon and the pkcheck client. This scales the verified PolkitBench corpus from 4,204 to 10,073 natural-language-to-Polkit-rule pairs at 100.0% AST validity and 99.7% runtime pass rate. Second, we conduct the per-component factorial ablation of structured context that was identified as future work in the precursor study: eight conditions C0-C7 are evaluated on GigaChat-10B-A1.8B with the new corpus. Three findings emerge. (i) The new harder corpus collapses the baseline mode (Syntax Valid 97.6% -> 58.5%, Combined Score 0.482 -> 0.252), whereas the context-enhanced mode degrades only marginally (Syntax 98.6% -> 97.4%, Combined 0.801 -> 0.750), confirming that structured context is not a cosmetic improvement but a load-bearing mechanism. (ii) The best absolute condition is the full context C7 across all metrics, while the strongest partial conditions (C5 = BNF + Vocabulary, C6 = API + Vocabulary) both contain the vocabulary. (iii) A Shapley-style decomposition assigns the largest semantic-quality effect to the vocabulary (Combined +0.198), the largest structural-validity effects to API (+24.7 pp) and BNF (+22.3 pp).

Related papers

• Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability [0.15635627702544694]
  This paper introduces a corpus of 10,000 Bangla sentences, manually annotated into four functional categories.<n>We evaluate multiple feature representations, including Bag-of-Words (BoW), TF-IDF, and Word2Vec.<n> Experimental results show that TF-IDF consistently outperforms Word2Vec.
  arXiv  Detail & Related papers  (2026-09-12T10:45:24Z)
• ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers [77.95933562142014]
  ITPEval is the first benchmark for evaluating automated formal proof translation across four major ITPs.<n>We release itpeval, a unified multi-ITP verification infrastructure with state-isolated warm backends.
  arXiv  Detail & Related papers  (2026-07-07T22:05:55Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Text2DSL: LLM-Based Code Generation for Domain-Specific Languages [78.29352305480285]
  This paper formalises the task of automatic DSL code generation from natural language descriptions - Text2.<n>We introduce the PolkitBench dataset comprising 4,204 verified natural-language-to-Polkit-rule pairs.
  arXiv  Detail & Related papers  (2026-06-21T16:44:20Z)
• Benchmarking Speech-to-Speech Translation Models [55.00303727199927]
  Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol.<n>We introduce a benchmarking framework integrating 46 metrics across eight dimensions.<n>We deploy it on 1,248 model-language configurations from FLEURS and CVSS.
  arXiv  Detail & Related papers  (2026-06-02T07:01:33Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• PHANTOM: Polymorphic Honeytoken Adaptation with Narrative-Tailored Organisational Mimicry [0.2538209532048867]
  Honeytokens are decoy digital assets planted to detect and unauthorised attribute access.<n>We introduce PHANTOM, a framework that generates contextually convincing honeytokens by encoding organisation-specific knowledge.<n>Results are reproduced without external API calls, making the pipeline fully deployable in air-gapped environments.
  arXiv  Detail & Related papers  (2026-05-04T17:14:13Z)
• PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution [2.28438857884398]
  LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows.<n>We introduce PRECEPT, a unified framework for test-time adaptation with three tightly coupled components.
  arXiv  Detail & Related papers  (2026-03-10T13:16:45Z)
• T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning [31.85615810584119]
  We introduce Structure of Thought (SoT), a prompting technique that guides models to construct intermediate text structures.<n>Building upon this insight, we present T2S-Bench, the first benchmark designed to evaluate and improve text-to-structure capabilities of models.
  arXiv  Detail & Related papers  (2026-03-04T07:05:09Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)
• VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models [3.4157048274143316]
  VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluation task for contextualized word embeddings. We show that VAST is useful for 7 other LMs, and can be used in 7 languages. We also show that 8 of 10 WEAT bias tests, which compare differences in word embedding associations between groups of words, exhibit more stereotype-congruent biases after isolating semantics.
  arXiv  Detail & Related papers  (2022-03-14T21:29:38Z)
• Grounded Compositional Outputs for Adaptive Language Modeling [59.02706635250856]
  A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size. We propose a fully compositional output embedding layer for language models. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
  arXiv  Detail & Related papers  (2020-09-24T07:21:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.