Graham Horwood

Muhammad Khalifa, Yogarshi Vyas, Shuai Wang et al. · amazon-science

We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured documents, as positional, layout, and style information play a vital role in interpreting such documents. The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge. We focus exclusively on the zero-shot setting where inference is done on new unseen classes. To address this task, we propose a matching-based approach that relies on a pairwise contrastive objective for both pretraining and fine-tuning. Our results show a significant boost in Macro F$_1$ from the proposed pretraining step in both supervised and unsupervised zero-shot settings.

Benjamin Hsu, Graham Horwood · amazon-science

Identifying related entities and events within and across documents is fundamental to natural language understanding. We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Earlier state-of-the-art methods have formulated this problem as a binary classification problem and leveraged large transformers in a cross-encoder architecture to achieve their results. For large collections of documents and corresponding set of $n$ mentions, the necessity of performing $n^{2}$ transformer computations in these earlier approaches can be computationally intensive. We show that it is possible to reduce this burden by applying contrastive learning techniques that only require $n$ transformer computations at inference time. Our method achieves state-of-the-art results on a number of key metrics on the ECB+ corpus and is competitive on others.

Mohammadtaher Safarzadeh, Hitesh Laxmichand Patel, Afshin Orojlooyjadid et al.

Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) benchmarks, yet their reported accuracy may be inflated by contamination from benchmark queries or structurally similar patterns seen during training. We introduce SPENCE (Syntactic Probing and Evaluation of NL2SQL Contamination Effects), a controlled syntactic probing framework for detecting and quantifying such contamination. SPENCE systematically generates syntactic variants of test queries for four widely used NL2SQL datasets-Spider, SParC, CoSQL, and the newer BIRD benchmark. We use SPENCE to evaluate multiple high-capacity LLMs under execution-based scoring. For each model, we measure changes in execution accuracy across increasing levels of syntactic divergence and quantify rank sensitivity using Kendall's tau with bootstrap confidence intervals. By aligning these robustness trends with benchmark release dates, we observe a clear temporal gradient: older benchmarks such as Spider exhibit the strongest negative values and thus the highest likelihood of training leakage, whereas the more recent BIRD dataset shows minimal sensitivity and appears largely uncontaminated. Together, these findings highlight the importance of temporally contextualized, syntactic-probing evaluation for trustworthy NL2SQL benchmarking.

Vinayak Arannil, Neha Narwal, Sourav Sanjukta Bhabesh et al.

Large Language Models (LLMs) have shown remarkable ability to generalize effectively across numerous industry domains while executing a range of tasks. Many of these competencies are obtained from the data utilized during the pre-training phase of the Language Models (LMs). However, these models exhibit limitations when tasked with performing in specialized or low-resource industry domains. More recent approaches use LLMs for generating domain-specific synthetic data but most often they lack in truthfulness and complexity. Alternatively, in cases where domain data is available like healthcare and finance most of the LMs are proprietary necessitating the need for a scalable method to curate real world industry specific pre-training data. In this work, we propose an automated and scalable framework - DoPAMine:Domain-specific Pre-training Adaptation from seed-guided data Mining, to mine domain specific training data from a large data corpus for domain adaptation of a LM. The framework leverages the parametric knowledge of a LLM to generate diverse and representative seed data tailored to a specific domain which is then used to mine real world data from a large data corpus like Common Crawl. We evaluated our framework's performance in the continual pre-training (CPT) setting by training two domain specific 7B parameter LMs in healthcare and finance with data mined via DoPAMine. Our experiments show that DoPAMine boosts the performance of pre-trained LLMs on average by 4.9% and 5.1% in zero-shot and 5-shot settings respectively on healthcare tasks from MMLU, MedQA, MedMCQA and PubMedQA datasets, and 2.9% and 6.7% for zero-shot and 5-shot settings respectively on finance tasks from FiQA-SA, FPB and Headlines datasets when compared to the baseline.

Jyotika Singh, Fang Tu, Aziza Mirzadova et al.

Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets. Most robustness variants apply surface-level perturbations (paraphrases, renamings, number swaps, distractors) that largely preserve the underlying facts, and static releases can themselves become memorization targets over time. We introduce GSM-SEM, a reusable and stochastic framework for generating semantically diverse benchmark variants with substantially higher semantic variance than prior approaches. GSM-SEM perturbs problem statements by modifying entities, attributes, and/or relationships, frequently altering underlying facts and requiring models to recompute solutions under new conditions, while constraining generation to preserve the original calculations/answer and approximate problem difficulty. GSM-SEM generates fresh variants on each run without requiring re-annotation, reducing reliance on static public benchmarks for evaluation and thereby lowering the bias of memorization. We apply GSM-SEM on GSM8K and two existing variation suites (GSM-Symbolic and GSM-Plus), producing GSM8K-SEM, GSM-Symbolic-SEM, and GSM-Plus-SEM. Evaluating 14 SOTA LLMs, we observe consistent performance drops with larger decline when semantic perturbations are coupled with symbolic/plus variations (average drop rate 28% in maximum strictness configuration of GSM-SEM). We publicly release the three SEM variants as fully human-validated datasets. Finally, to demonstrate applicability beyond GSM-style math problems, we apply GSM-SEM to additional benchmarks including BigBenchHard, LogicBench, and NLR-BIRD.

Evangelia Spiliopoulou, Riccardo Fogliato, Hanna Burnsky et al.

Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias, which can distort evaluations of true model performance. Previous studies often conflate genuine differences in model quality with bias or incorrectly assume that evaluations from LLMs and humans follow the same rating distributions. In this work, we present a statistical framework that explicitly formalizes assumptions under which self-bias can be identified and estimated. Our method models the difference in the scoring distribution that LLM-as-a-judge assigns to its own completions compared to other models, while accounting for the underlying quality of the completions provided by an independent, third-party judge (e.g., humans). Our method reliably isolates and quantifies self-bias, even when models vary in ability, ensuring that genuine performance differences are not mistaken for self-bias. We conduct an empirical analysis of self-bias on a large dataset (>5000 prompt-completion pairs) consisting of expert human annotations and judgments from nine different LLM judges. We find that some models, such as GPT-4o and Claude 3.5 Sonnet, systematically assign higher scores to their own outputs. These models also display family-bias; systematically assigning higher ratings to outputs produced by other models of the same family. Our findings highlight potential pitfalls of using LLM judges and offer practical guidance to mitigate biases when interpreting automated evaluations.

Haris Riaz, Sourav Bhabesh, Vinayak Arannil et al.

Recent smaller language models such Phi-3.5 and Phi-4 rely on synthetic data generated using larger Language models. Questions remain about leveraging synthetic data for other use cases, such as adapting LLMs to specific domains. A key limitation of synthetic data is low diversity, which negatively impacts its downstream applicability for improving other models. To address this, we propose MetaSynth, a method for generating synthetic data that enhances diversity through meta-prompting, where a language model orchestrates multiple "expert" LLM agents to collaboratively generate data. Using only 25 million tokens of synthetic data generated with MetaSynth, we successfully adapt a well-trained LLM (Mistral-7B-v0.3) to two specialized domains-Finance and Biomedicine-without compromising the capabilities of the resulting model in general tasks. In addition, we evaluate the diversity of our synthetic data using seven automated metrics, and find that it approaches the diversity of LLM pre-training corpora. Continually pre-training Mistral-7B-v0.3 with MetaSynth notably outperforms the base LLM, showing improvements of up to 4.08% in Finance and 13.75% in Biomedicine. The same model shows degraded performance when trained on data generated using a template prompt, even when the template includes prior generations and varying In-Context exemplars of real data. Our findings suggest that a few million tokens of diverse synthetic data without mixing any real data, is sufficient for effective domain adaptation when using MetaSynth.

Karan Dua, Hitesh Laxmichand Patel, Puneet Mittal et al.

Developing document understanding models at enterprise scale requires large, diverse, and well-annotated datasets spanning a wide range of document types. However, collecting such data is prohibitively expensive due to privacy constraints, legal restrictions, and the sheer volume of manual annotation needed - costs that can scale into millions of dollars. We introduce FlexDoc, a scalable synthetic data generation framework that combines Stochastic Schemas and Parameterized Sampling to produce realistic, multilingual semi-structured documents with rich annotations. By probabilistically modeling layout patterns, visual structure, and content variability, FlexDoc enables the controlled generation of diverse document variants at scale. Experiments on Key Information Extraction (KIE) tasks demonstrate that FlexDoc-generated data improves the absolute F1 Score by up to 11% when used to augment real datasets, while reducing annotation effort by over 90% compared to traditional hard-template methods. The solution is in active deployment, where it has accelerated the development of enterprise-grade document understanding models while significantly reducing data acquisition and annotation costs.