paper-with-me

홈 › Papers

VeriTrans: Fine-Tuned LLM-Assisted NL-to-PL Translation via a Deterministic Neuro-Symbolic Pipeline

2026-04-11 · Xuan Liu, Dheeraj Kodakandla, Kushagra Srivastva, Mahfuza Farooque arxiv

\textbf{VeriTrans} is a reliability-first ML system that compiles natural-language requirements into solver-ready logic with validator-gated reliability. The pipeline integrates an instruction-tuned NL$\!\to\!$PL translator, round-trip reconstruction (PL$\!\to\!$NL) used as a high-precision acceptance gate, and canonical PL$\!\to\!$CNF compilation, all executed via fixed API configuration (temperature$=0$; fine-tuning runs use seed$=42$) and per-item artifact logging (prompts, outputs, hashes) to support auditability and replay-driven debugging. On \textbf{SatBench} (2{,}100 specifications), VeriTrans achieves 94.46\% SAT/UNSAT correctness and 87.73\% median round-trip similarity. Compact fine-tuning on 100--150 curated examples improves fidelity by about 1--1.5\,pp without increasing latency (mean 25.8\,s/spec on our 201-spec runtime subset). A thresholded acceptance policy on the round-trip score exposes a reliability--coverage knob: at $τ{=}75$, roughly 68\% of items are retained with $\sim$94\% correctness on the accepted set. Validator overhead contributes $<15\%$ of end-to-end runtime, and all prompts/responses and timing metadata are logged to enable replay-driven debugging and regression testing. By separating learned translation from symbolic verification and enforcing deterministic, validator-gated acceptance, VeriTrans turns NL$\!\to\!$logic front-ends into auditable, reproducible components for reliability-critical workflows.

📄 PDF Abstract BibTeX arXiv:2604.10341

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OPUS-CAT: Desktop NMT with CAT integration and local fine-tuning

2021-04-01 · EACL 2021 2 · Tommi Nieminen

OPUS-CAT is a collection of software which enables translators to use neural machine translation in computer-assisted translation tools without exposing themselves to security and confidentiality risks inherent in online…

Machine TranslationNMTTranslation

TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes

2023-11-17 · Bibek Upadhayay, Vahid Behzadan

Creating multilingual LLMs poses a significant challenge. Pretraining or fine-tuning LLMs to adopt new languages is evidently very costly. Furthermore, there exist limitations concerning benchmark datasets and the metric…

Cross-Lingual TransferTranslation

Q-Bridge: Code Translation for Quantum Machine Learning via LLMs

2026-03-29 · Runjia Zeng, Priyabrata Senapati, Ruixiang Tang, Dongfang Liu 외 arxiv

Large language models have recently shown potential in bridging the gap between classical machine learning and quantum machine learning. However, the lack of standardized, high-quality datasets and robust translation fra…

Quantum Machine LearningCode TranslationCode Generation

Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains

2024-02-28 · Vilém Zouhar, Shuoyang Ding, Anna Currey, Tatyana Badeka 외

We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this dataset to investigate whether machine translation (MT) metrics whic…

Machine TranslationTranslation

Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation

2024-04-02 · Veronica Valeros, Anna Širokova, Carlos Catania, Sebastian Garcia

Understanding cybercrime communications is paramount for cybersecurity defence. This often involves translating communications into English for processing, interpreting, and generating timely intelligence. The problem is…

Machine TranslationTranslation