Vadim Sheinin

Ngoc Phuoc An Vo, Brent Paulovicks, Vadim Sheinin

Given recent advancements of Large Language Models (LLMs), code generation tasks attract immense attention for wide application in different domains. In an effort to evaluate and select a best model to automatically remediate system incidents discovered by Application Performance Monitoring (APM) platforms, it is crucial to verify if the generated code is syntactically and semantically correct, and whether it can be executed correctly as intended. However, current methods for evaluating the quality of code generated by LLMs heavily rely on surface form similarity metrics (e.g. BLEU, ROUGE, and exact/partial match) which have numerous limitations. In contrast, execution based evaluation focuses more on code functionality and does not constrain the code generation to any fixed solution. Nevertheless, designing and implementing such execution-based evaluation platform is not a trivial task. There are several works creating execution-based evaluation platforms for popular programming languages such as SQL, Python, Java, but limited or no attempts for scripting languages such as Bash and PowerShell. In this paper, we present the first execution-based evaluation platform in which we created three test suites (total 125 handcrafted test cases) to evaluate Bash (both single-line commands and multiple-line scripts) and PowerShell codes generated by LLMs. We benchmark seven closed and open-source LLMs using our platform with different techniques (zero-shot vs. few-shot learning).

Matthew Peroni, Franck Le, Vadim Sheinin

The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that encourage desirable model properties. Prior work has mainly focused on crafting high-quality priors over generators to improve overall pretraining performance. Our insight is that parameterizing the generator distribution enables an adversarial robustness perspective: during training, we can adapt the generator to emphasize datasets that are particularly challenging for the model. We formalize this by introducing an optimality gap measure, given by the difference between TFM performance and the best achievable performance as estimated by strong baselines such as XGBoost, CatBoost, and Random Forests. Building on this idea, we propose Robust Tabular Foundation Models (RTFM), a model-agnostic adversarial training framework. Applied to the TabPFN V2 classifier, RTFM improves benchmark performance, with up to a 6% increase in mean normalized AUC over the original TabPFN and other baseline algorithms, while requiring less than 100k additional synthetic datasets. These results highlight a promising new direction for targeted adversarial training and fine-tuning of TFMs using synthetic data alone.

Ngoc Phuoc An Vo, Brent Paulovicks, Vadim Sheinin

In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is syntactically and semantically correct and whether it can be executed correctly as intended. There are three approaches: 1) conventional methods use surface form similarity metrics (token match, exact match, etc.) which have numerous limitations, 2) execution-based evaluation focuses more on code functionality based on pass/fail judgments for given test-cases, and 3) LLM-as-a-Judge employs LLMs for automated evaluation to judge if it is a correct answer for a given problem based on pre-defined metrics. In this work, we focused on enhancing LLM-as-a-Judge using bidirectional functionality matching and logic representation for reference-less automatic validation and refinement for Bash code generation to select the best model for automatic incident remediation in IT Automation. We used execution-based evaluation as ground-truth to evaluate our LLM-as-a-Judge metrics. Results show high accuracy and agreement with execution-based evaluation (and up to 8% over baseline). Finally, we built Reflection code agents to utilize judgments and feedback from our evaluation metrics which achieved significant improvement (up to 24% increase in accuracy) for automatic code refinement.

Irene Manotas, Octavian Popescu, Ngoc Phuoc An Vo et al.

There are many recent advanced developments for the Text-to-SQL task, where the Picard model is one of the the top performing models as measured by the Spider dataset competition. However, bringing Text-to-SQL systems to realistic use-cases through domain adaptation remains a tough challenge. We analyze how well the base T5 Language Model and Picard perform on query structures different from the Spider dataset, we fine-tuned the base model on the Spider data and on independent databases (DB). To avoid accessing the DB content online during inference, we also present an alternative way to disambiguate the values in an input question using a rule-based approach that relies on an intermediate representation of the semantic concepts of an input question. In our results we show in what cases T5 and Picard can deliver good performance, we share the lessons learned, and discuss current domain adaptation challenges.

Franck Le, Keith Grueneberg, Erich Nahum et al.

Tabular data are central to many real-world systems. While recent tabular transformers and in-context learners such as SAINT, TP-BERTa, TabPFN, TabICL, and MITRA incorporate limited inter-row reasoning, most approaches still lack an explicit mechanism to model relationships among instances, even though similar samples often share related outcomes. We investigate whether introducing \emph{simple graph priors} can enhance \emph{pretrained tabular transformers}. Concretely, we introduce {BOLERO}, a lightweight, static bipartite graph head that augments {RoBERTa-Tab} (a RoBERTa-style tabular backbone pretrained with masked-token prediction.) Each instance connects to feature/value anchors; a small GNN refines row representations, while the backbone remains frozen. We evaluate on 80 classification and 64 regression datasets from the TP-BERTa benchmark suites, comparing against strong baselines including XGBoost, CatBoost, TabPFN-v2, MITRA, TabICL, TP-BERTa, and RoBERTa-Tab. To ensure statistically sound conclusions, we follow best practices for multi-dataset evaluation: pairwise Wilcoxon signed-rank tests on per-dataset score differences and effect sizes (median improvement with confidence intervals), rather than mean-rank post-hoc tests that depend on the competitor pool. BOLERO achieves the highest number of statistically significant wins across both classification and regression, demonstrating that lightweight graph priors meaningfully improve pretrained tabular transformers.

Ngoc Phuoc An Vo, Irene Manotas, Octavian Popescu et al.

Business Process Management (BPM) is the discipline which is responsible for management of discovering, analyzing, redesigning, monitoring, and controlling business processes. One of the most crucial tasks of BPM is discovering and modelling business processes from text documents. In this paper, we present our system that resolves an end-to-end problem consisting of 1) recognizing conditional sentences from technical documents, 2) finding boundaries to extract conditional and resultant clauses from each conditional sentence, and 3) categorizing resultant clause as Action or Consequence which later helps to generate new steps in our business process model automatically. We created a new dataset and three models solve this problem. Our best model achieved very promising results of 83.82, 87.84, and 85.75 for Precision, Recall, and F1, respectively, for extracting Condition, Action, and Consequence clauses using Exact Match metric.

Kun Xu, Lingfei Wu, Zhiguo Wang et al.

Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query. In this paper, we first introduce a strategy to represent the SQL query as a directed graph and then employ a graph-to-sequence model to encode the global structure information into node embeddings. This model can effectively learn the correlation between the SQL query pattern and its interpretation. Experimental results on the WikiSQL dataset and Stackoverflow dataset show that our model significantly outperforms the Seq2Seq and Tree2Seq baselines, achieving the state-of-the-art performance.

Kun Xu, Lingfei Wu, Zhiguo Wang et al.

Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper, we first propose to use the \textit{syntactic graph} to represent three types of syntactic information, i.e., word order, dependency and constituency features. We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form. Experimental results on benchmark datasets show that our model is comparable to the state-of-the-art on Jobs640, ATIS and Geo880. Experimental results on adversarial examples demonstrate the robustness of the model is also improved by encoding more syntactic information.

Kun Xu, Lingfei Wu, Zhiguo Wang et al.

The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form to the appropriate sequence. To address this challenge, we introduce a novel general end-to-end graph-to-sequence neural encoder-decoder model that maps an input graph to a sequence of vectors and uses an attention-based LSTM method to decode the target sequence from these vectors. Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings. We further introduce an attention mechanism that aligns node embeddings and the decoding sequence to better cope with large graphs. Experimental results on bAbI, Shortest Path, and Natural Language Generation tasks demonstrate that our model achieves state-of-the-art performance and significantly outperforms existing graph neural networks, Seq2Seq, and Tree2Seq models; using the proposed bi-directional node embedding aggregation strategy, the model can converge rapidly to the optimal performance.