Newest papers

From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution

Amit Lisha, Reut Tsarfaty · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28311 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Menginterpretasikan instruksi abstrak membutuhkan model untuk mengidentifikasi abstraksi yang sama yang dimaksudkan oleh pembicara, dan membongkarnya ke dalam banyak tindakan konkret yang menginstansifikasikannya. Model bahasa laytex berjuang di sini: pekerjaan sebelumnya telah menunjukkan bahwa kinerja primitif yang didokumentasikan melemah karena tingkat abstraksi dalam instruksi meningkat. Untuk memajukan kesenjangan antara abstraksi bahasa alami dan tindakan konkret, kami mengusulkan untuk meminjam dari lingkungan pengkodean gagasan dari sebuah bahasa spesifik domain (DSL), lapisan representasi eksplisit di mana nama-nama komunitas yang didokumentasikan melemah karena abstraksi yang berulang yang berkembang menjadi tindakan konkret. Untuk menunjukkan efektivitas DSL untuk interpretasi bahasa NL secara singkat pada \texts{Hexagons}, kami menyarankan bahwa model-model yang terus berlan

Machine translation (Meta M2M100); the English original follows.

Abstract

Natural-language instructions often rely on high-level abstractions, such as asking an agent to ``stack blocks in a pyramid.'' Interpreting abstract instructions requires models to both identify the abstraction intended by the speaker, and unroll it into the many concrete actions that instantiate it. Language models struggle here: prior work has shown that performance degrades as the level of abstraction in the instruction rises. To bridge the gap between natural language abstraction and concrete actions, we propose to borrow from coding environments the notion of a {\em domain-specific language} (DSL), an explicit representation layer whose documented primitives name recurring abstractions that expand into concrete actions. We demonstrate the efficacy of DSLs for NL interpretation on \textsc{Hexagons}, a visually-grounded instruction-following task graded for abstraction. We further ask whether language models can induce such DSLs themselves from domain data. Our results show that while code generation consistently improves over direct inference, code generation over a human-curated DSL yields dramatic gains, up to 10 absolute F1 points, reaching the human skyline, with gains concentrated at {\em higher} abstraction levels. We confirm this pattern on the \textsc{Text2CAD} benchmark. At the same time, model-induced DSLs recover only part of this gain, remaining inconsistent across runs and short of their human-curated counterpart. Overall, the right representation closes much of the gap caused by high abstraction --- but inducing that layer of representation automatically is where models still fall short, and where we see a strong opportunity for the community to make progress.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Abstraction, Computer science, Programming language, Interpretation (philosophy), Representation (politics), Abstract interpretation

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange