Synthetic Benchmark Generation

Follow this topic Ask about this topic

Synthetic benchmark generation creates evaluation tasks and datasets when real examples are scarce, costly, private, contaminated, or too fixed to expose specific weaknesses. Approaches include procedural generators and simulators, LLM- or agent-driven task synthesis, and solver-backed construction with executable checks for answers, feasibility, and difficulty. These methods support fresh, adjustable tests across areas such as reasoning, coding, robotics, retrieval, and scientific workflows, often with ground truth known by construction. A central challenge is balancing control and verifiability with realistic, diverse tasks that transfer to real settings, while avoiding artifacts or shared generation and evaluation rules that inflate scores.

Latest papers

289 papers26 papers in the last four weeks, down 16% on the four weeks before. 0.2% of all new papers.

Feb 16, 2026

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations. Current LLM-based SAE benchmarks are too noisy to differentiate architectural improvements, while commonly used synthetic-data experiments are too small-scale, unstandardized, and unrealistic to be meaningful. We introduce SynthSAEBench, a benchmark and toolkit for evaluating SAEs against large-scale synthetic data with realistic feature characteristics including correlation, hierarchy, and superposition, while providing ground-truth features and firings. SynthSAEBench acts as a controlled lower-bound test: SAE architectures that fail when the Linear Representation Hypothesis holds by construction have little hope on real LLMs. The benchmark reproduces known LLM SAE phenomena including the disconnect between reconstruction and latent quality, poor SAE probing, and a precision-recall trade-off mediated by L0, demonstrating that SynthSAEBench findings reproduce results on LLM SAEs. We further identify a novel failure mode: Matching Pursuit SAEs exploit superposition noise to improve reconstruction without learning ground-truth features, suggesting more expressive encoding procedures can easily overfit. SynthSAEBench complements LLM benchmarks with ground-truth features and controlled ablations for diagnosing SAE failure modes, while providing a clear target for SAE architecture work.

David Chanin, Adrià Garriga-Alonso

University College London · 2MATS · 3Decode Research

Sparse Autoencoders Synthetic Benchmark Generation Synthetic Data Evaluation

Jan 20, 2026

LogicEnvGen: Task-Logic Driven Generation of Diverse Simulated Environments for Embodied AI

Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout coherence), overlooking a crucial aspect: logical diversity from the testing perspective. This limits the comprehensive evaluation of embodied agent adaptability and planning robustness across distinct simulated environments. To bridge this gap, we propose LogicEnvGen, a novel method driven by Large Language Models (LLMs) that adopts a top-down paradigm to generate logically diverse simulated environments as test cases for agents. Given an agent task, LogicEnvGen first analyzes its execution logic to construct decision-tree-structured behavior plans and then synthesizes a set of logical trajectories. Subsequently, it adopts a heuristic algorithm to refine the trajectory set, reducing redundant simulation. For each logical trajectory, which represents a potential task situation, LogicEnvGen correspondingly instantiates a concrete simulated environment. Furthermore, we introduce LogicEnvEval, a novel benchmark for simulated environment generation, with four quantitative metrics. Experimental results verify the lack of logical diversity in baselines and demonstrate that LogicEnvGen achieves 1.08-2.67x greater diversity, significantly improving the performance in revealing agent faults by 3.34%-72.00%.

Jianan Wang, Siyang Zhang, Bin Li +4

College of Computer Science and Technology, National University of Defense Technology · Intelligent Game and Decision Lab (IGDL), Beijing · School of Artifical Intelligence, Shanghai Jiao Tong University

Robotics Simulation AI Agent Evaluation Synthetic Benchmark Generation Embodied AI

Jan 19, 2026

An Evolutionary Framework for Automatic Optimization Benchmark Generation via Large Language Models

Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capture the diversity and irregularity of real-world problem structures, while benchmarks derived from real-world problems are costly and difficult to construct. To address these challenges, we propose an evolutionary automatic benchmark generation framework that leverages a large language model (LLM) as a generative operator, termed the LLM-driven evolutionary benchmark generator (LLM-EBG). In this framework, the LLM serves as an evolutionary operator that generates and evolves benchmark problems within a flexible, expressive representation space. As a case study, we generate unconstrained single-objective continuous minimization problems represented as mathematical expressions designed to induce significant performance differences between a genetic algorithm (GA) and differential evolution (DE). Experimental results show that LLM-EBG successfully produces benchmark problems in which the designated target algorithm consistently outperforms the comparative algorithm in more than 80% of trials. Furthermore, exploratory landscape analysis reveals that benchmarks favoring GA are highly sensitive to variable scaling, demonstrating that the proposed framework can generate problems with distinct geometric characteristics that reflect the intrinsic search behaviors of different optimization algorithms.

Yuhiro Ono, Tomohiro Harada, Yukiya Miura

Graduate School of Systems Design, Tokyo Metropolitan University, 6-6, Asahigaoka, Hino, 1910065, Tokyo, Japan. · Graduate School of Science and Engineering, Saitama University, 2552026 Shimo-okubo, Sakura-ku, Saitama, 3388570, Saitama, Japan.

Evolutionary Optimization Benchmark Design Synthetic Benchmark Generation

Jan 16, 2026

SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models

Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems. As a result, recent work incorporates some 3D tasks (such as depth estimation) into VFM training. However, VFM performance remains inconsistent across other spatial tasks, raising the question of whether these models truly have spatial awareness or overfit to specific 3D objectives. To address this question, we introduce the Spatial Relation Recognition Task (SpaRRTa) benchmark, which evaluates the ability of VFMs to identify relative positions of objects in the image. Unlike traditional 3D objectives that focus on precise metric prediction (e.g., surface normal estimation), SpaRRTa probes a fundamental capability underpinning more advanced forms of human-like spatial understanding. SpaRRTa generates an arbitrary number of photorealistic images with diverse scenes and fully controllable object arrangements, along with freely accessible spatial annotations. Evaluating a range of state-of-the-art VFMs, we reveal significant disparities between their spatial reasoning abilities. Through our analysis, we provide insights into the mechanisms that support or hinder spatial awareness in modern VFMs. We hope that SpaRRTa will serve as a useful tool for guiding the development of future spatially aware visual models.

Turhan Can Kargin, Wojciech Jasiński, Adam Pardyl +2

Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland. · Doctoral School of Exact and Natural Sciences, Jagiellonian University, Kraków, Poland. · AGH University of Krakow, Kraków, Poland. +3

Spatial Reasoning Benchmarks Visual Spatial Reasoning Vision Foundation Models Synthetic Benchmark Generation

Jan 12, 2026

Kinship Data Benchmark for Multi-hop Reasoning

Multi-hop kinship reasoning is a natural testbed for LLM compositionality, but existing benchmarks (notably CLUTRR) cover only the descriptive Eskimo system. We introduce KinshipQA, a procedurally-generated benchmark covering seven anthropologically-documented kinship systems (Eskimo, Sudanese, Hawaiian, Iroquois, Dravidian, Crow, Omaha) and up to six reasoning hops, with a tunable simulator horizon that eliminates exact-instance pretraining overlap. Evaluating six LLMs, we find a 40.9% accuracy drop when reasoning shifts from biological multi-hop to culturally-marked classification on the five non-descriptive systems. The drop holds for every non-descriptive system and is largest for the two skewing systems (Crow, Omaha), persists under chain-of-thought and few-shot prompting, and compounds with depth: at 5--6 hops cultural override falls to 10.6% while biological composition over the same chains remains at 58.6%. Under identical rule access humans reach 89.0% versus 50.7% for LLMs, so the questions are reliably solvable once the rule is supplied. Two follow-up experiments suggest distinct contributors. A fictional-rule control swapping system labels and kin terms for invented strings raises accuracy by 6.1%, implicating familiar English surface forms. An in-context-rule probe prepending the override rule helps skewing systems (+17.1%) but hurts non-skewing systems whose baseline already exceeds about 60% (-13.4%), consistent with a missing skewing prior alongside rule interference where the model already has a working approximation. Our code and data are publicly available on GitHub.

Tianda Sun, Dimitar Kazakov

Department of Computer Science University of York, UK

LLM Evaluation Synthetic Benchmark Generation Multi-Hop Reasoning

Jan 5, 2026

Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot

The development of robust and generalizable robot learning models is critically contingent upon the availability of large-scale, diverse training data and reliable evaluation benchmarks. Collecting data in the physical world poses prohibitive costs and scalability challenges, and prevailing simulation benchmarks frequently suffer from fragmentation, narrow scope, or insufficient fidelity to enable effective sim-to-real transfer. To address these challenges, we introduce Genie Sim 3.0, a unified simulation platform for robotic manipulation. We present Genie Sim Generator, a large language model (LLM)-powered tool that constructs high-fidelity scenes from natural language instructions. Its principal strength resides in rapid and multi-dimensional generalization, facilitating the synthesis of diverse environments to support scalable data collection and robust policy evaluation. We introduce the first benchmark that pioneers the application of LLM for automated evaluation. It leverages LLM to mass-generate evaluation scenarios and employs Vision-Language Model (VLM) to establish an automated assessment pipeline. We also release an open-source dataset comprising more than 10,000 hours of synthetic data across over 200 tasks. Through systematic experimentation, we validate the robust zero-shot sim-to-real transfer capability of our open-source dataset, demonstrating that synthetic data can server as an effective substitute for real-world data under controlled conditions for scalable policy training. For code and dataset details, please refer to: https://github.com/AgibotTech/genie_sim.

Chenghao Yin, Da Huang, Di Yang +16

Robotic Data Collection Robotics Simulation Synthetic Data Generation for Robotics Synthetic Benchmark Generation Robot Manipulation Benchmarks

Nov 22, 2025

Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks

Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchmarks lack the scene diversity, balanced anomaly coverage, and temporal complexity needed to reliably assess real-world performance. Meanwhile, the community is increasingly moving toward Video Anomaly Understanding (VAU), which requires deeper semantic and causal reasoning but remains difficult to benchmark due to the heavy manual annotation effort it demands. In this paper, we introduce Pistachio, a new VAD/VAU benchmark constructed entirely through a controlled, generation-based pipeline. By leveraging recent advances in video generation models, Pistachio provides precise control over scenes, anomaly types, and temporal narratives, effectively eliminating the biases and limitations of Internet-collected datasets. Our pipeline integrates scene-conditioned anomaly assignment, multi-step storyline generation, and a temporally consistent long-form synthesis strategy that produces coherent 41-second videos with minimal human intervention. Extensive experiments demonstrate the scale, diversity, and complexity of Pistachio, revealing new challenges for existing methods and motivating future research on dynamic and multi-event anomaly understanding.

Jie Li, Hongyi Cai, Mingkang Dong +4

Shanghai Jiao Tong University · University of Science & Technology Beijing · Universiti Malaya +2

Synthetic Benchmark Generation Video Anomaly Detection Synthetic Anomaly Generation Synthetic Video Detection Benchmarks

Nov 6, 2025

Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs

Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various solutions have been proposed, a comparison of methods is difficult due to the lack of challenging QA datasets with ground-truth targets for graph retrieval. We present SynthKGQA, an LLM-powered framework for generating high-quality Knowledge Graph Question Answering datasets from any Knowledge Graph, providing the full set of ground-truth facts in the KG to reason over questions. To demonstrate its utility, we apply SynthKGQA to ogbl-wikikg2, a Wikidata-derived KG, and validate generated items against an up-to-date dump of Wikidata to create GTSQA. This new dataset is specifically designed to test zero-shot generalization with respect to unseen graph structures and relation types, enabling us to analyze the abilities and limitations of SOTA graph retrieval approaches at an unprecedented level of granularity. We also show that KG retrievers trained on GTSQA can transfer to a human-curated benchmark, and that the ground-truth subgraphs produced by SynthKGQA provide a better training supervision signal than previously-used heuristics.

Alberto Cattaneo, Carlo Luschi, Daniel Justus

Graphcore AI Research

Graph Retrieval-Augmented Generation Synthetic Benchmark Generation RAG Evaluation Knowledge Graph Question Answering

Aug 21, 2025

SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking

The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM safety evaluation benchmarks are proposed. However, existing benchmarks generally rely on labor-intensive manual curation, which causes excessive time and resource consumption. They also exhibit significant redundancy and limited difficulty. To alleviate these problems, we introduce SafetyFlow, the first agent-flow system designed to automate the construction of LLM safety benchmarks. SafetyFlow can automatically build a comprehensive safety benchmark in only four days without any human intervention by orchestrating seven specialized agents, significantly reducing time and resource cost. Equipped with versatile tools, the agents of SafetyFlow ensure process and cost controllability while integrating human expertise into the automatic pipeline. The final constructed dataset, SafetyFlowBench, contains 23,446 queries with low redundancy and strong discriminative power. Our contribution includes the first fully automated benchmarking pipeline and a comprehensive safety benchmark. We evaluate the safety of 49 advanced LLMs on our dataset and conduct extensive experiments to validate our efficacy and efficiency.

Xiangyang Zhu, Yuan Tian, Chunyi Li +3

Shanghai AI Lab · East China Normal University

LLM Safety Benchmarks Synthetic Benchmark Generation LLM Safety Evaluation AI Agent Safety Benchmarks

Jul 4, 2025

Instance Generation for Patient-to-room Assignment and Admission Scheduling Based on Real Hospital Data

Developing algorithms for real-life problems that perform well in practice depends on the availability of realistic data for testing. Obtaining real-life data for optimization problems in health care, however, is often difficult, and such data typically cannot be published, which limits reproducibility by other researchers. This is especially true for patient-related problems because of data privacy policies such as the patient-to-room assignment problem. Therefore, artificially generated instances are commonly used. To improve the generation of realistic instances, we develop a configurable instance generator for the patient-to-room assignment problem and other patient-related problems, featuring an easy-to-use graphical user interface. The design of the generator is based on an extensive empirical analysis of real hospital data, which identifies relevant ward-specific patterns such as patients' age and length-of-stay distributions. Moreover, as randomly generated instances are often infeasible, we address this issue in two ways. We implement a dynamic programming approach in the generator to optionally enforce feasibility and extend existing results from the literature to derive new combinatorial insights into patient-to-room feasibility.

Tabea Brandt, Christina Büsing, Johanna Leweke +2

Chair of Combinatorial Optimization, RWTH Aachen University, Im Süsterfeld 9, 52072 Aachen, Germany · Chair of Algorithms and Complexity, RWTH Aachen University, Ahornstraße 55, 52074 Aachen, Germany

Healthcare Dynamic Programming Synthetic Data Generation Synthetic Benchmark Generation

Jun 11, 2025

ToxSyn-PT: A Synthetic Fine-Grained Dataset of Minority-Targeted Toxic Language in Portuguese

The development of robust hate speech detection systems remains limited by the lack of large-scale, fine-grained training data, especially for languages beyond English. Existing corpora typically rely on simplistic toxic and non-toxic labels, and the few that capture hate directed at specific minority groups lack the positive counterexamples required to distinguish genuine hate from mere discussion. In this work, we introduce ToxSyn-PT, the first Portuguese large-scale corpus explicitly designed for multi-label hate speech detection across nine protected minority groups, including the non-toxic counterexamples absent in all other public datasets. Generated via a controllable four-stage pipeline, ToxSyn contains discourse-type annotations to capture rhetorical strategies of toxic/non-toxic language, such as sarcasm, dehumanization, and cultural appreciation. Our experiments reveal a catastrophic, mutual generalization failure compared to existing datasets from social-media domains: models trained on social media struggle to generalize to minority-specific contexts, and vice-versa. This finding indicates they are distinct tasks and exposes summary metrics like Macro F1 can be unreliable indicators of true model behavior, as they completely mask model failure. We publicly release ToxSyn on HuggingFace to support reproducible research on synthetic data generation and benchmark progress in hate-speech detection for low- and mid-resource languages.

Iago Alves Brito, Julia Soares Dollis, Fernanda Bufon Farber +2

Advanced Knowledge Center for Immersive Technologies (AKCIT) · Federal University of Goiás

Synthetic Data Generation Hate Speech Detection Synthetic Benchmark Generation Low-Resource Language Processing

May 29, 2025

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics

Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from domain specifics to examine reasoning as a capability in and of itself. We contribute a novel type of benchmark evaluating the inductive reasoning capabilities of LLMs that is inspired by the forward reconstruction task from historical linguistics but is formulated in an extremely simple, general way (in the form of Programming by Examples). The task involves generating a cascade of simple string rewrite programs to transform a given list of input strings into a list of desired output strings. We present a fully automated pipeline that programmatically generates problems of this type with controllable difficulty, enabling scalable evaluation of reasoning models while avoiding contamination. Using this approach, we construct two benchmarks: PBEBench-Lite, which efficiently stratifies models of varying capabilities, and PBEBench, which requires models to induce programs similar in complexity to those constructed by historical linguists. Our experiments reveal a substantial performance gap between models that leverage test-time compute or LCoT (long chain-of-thought) reasoning and those that do not. Moreover, although recent models show promise, the solve rate for both of them drops below 5% for hard instances of the PBEBench dataset (ground truth cascade lengths of 20 and 30, respectively), falling well short of realistic historical linguistics requirements even with computationally expensive, popular scaling techniques from the PBE and reasoning literature. Additionally, we also study the effectiveness of different scaling strategies and the impact of various hyperparameters on the difficulty of the generated data using gpt-oss-120b, the best-performing open-source model.

Atharva Naik, Prakam, Yash Mathur +6

Carnegie Mellon University · Independent Researcher · Ohio State University

Program Synthesis Inductive Inference LLM Evaluation Logical Reasoning Synthetic Benchmark Generation LLM Reasoning+1

May 21, 2025

Synthetic Enclosed Echoes: A New Dataset to Mitigate the Gap Between Simulated and Real-World Sonar Data

This paper introduces Synthetic Enclosed Echoes (SEE), a novel dataset designed to enhance robot perception and 3D reconstruction capabilities in underwater environments. SEE comprises high-fidelity synthetic sonar data, complemented by a smaller subset of real-world sonar data. To facilitate flexible data acquisition, a simulated environment has been developed, enabling the generation of additional data through modifications such as the inclusion of new structures or imaging sonar configurations. This hybrid approach leverages the advantages of synthetic data, including readily available ground truth and the ability to generate diverse datasets, while bridging the simulation-to-reality gap with real-world data acquired in a similar environment. The SEE dataset comprehensively evaluates acoustic data-based methods, including mathematics-based sonar approaches and deep learning algorithms. These techniques were employed to validate the dataset, confirming its suitability for underwater 3D reconstruction. Furthermore, this paper proposes a novel modification to a state-of-the-art algorithm, demonstrating improved performance compared to existing methods. The SEE dataset enables the evaluation of acoustic data-based methods in realistic scenarios, thereby improving their feasibility for real-world underwater applications.

Guilherme de Oliveira, Matheus M. dos Santos, Paulo L. J. Drews-Jr

NAUTEC - Intelligent robotics and automation group, FURG - Federal University of Rio Grande, Rio Grande, RS, Brazil · ICMC - Institute of Mathematics and Computer Sciences, USP - University of S˜ao Paulo, S˜ao Carlos, SP, Brazil

Synthetic-to-Real Domain Adaptation Underwater Imaging 3D Reconstruction Synthetic Data Generation Synthetic Benchmark Generation Underwater 3D Reconstruction

May 19, 2025

Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings

We propose a novel benchmarking methodology for graph neural networks (GNNs) based on the graph alignment problem, a combinatorial optimization task that generalizes graph isomorphism by aligning two unlabeled graphs to maximize overlapping edges. We frame this problem as a self-supervised learning task and present several methods to generate graph alignment datasets using synthetic random graphs and real-world graph datasets from multiple domains. For a given graph dataset, we generate a family of graph alignment datasets with increasing difficulty, allowing us to rank the performance of various architectures. Our experiments prove that there is an optimal task difficulty for having a statistically relevant ranking of different models and that, even on a structure-only task, anisotropic models perform better compared to isotropic ones. To further prove that our synthetic task capture meaningful information, we show its effectiveness for self-supervised GNN pre-training: the learned node embeddings can be leveraged as positional encodings by transformers for graph regression or can be used to reconstruct the full structure of the graph with

98\%

accuracy. To support reproducibility and further research, we provide an open-source Python package to generate graph alignment datasets and benchmark new GNN architectures. The source code is available at https://github.com/adrien-lagesse/graph-alignment-benchmark.

Adrien Lagesse, Marc Lelarge

INRIA, École Normale Supérieure - PSL, Paris, France.

Graph Neural Networks Synthetic Benchmark Generation Positional Encoding Graph Matching

May 19, 2025

AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD

Scientific machine learning uses simulation data to train surrogate models for fast physical-field prediction across geometries. Local shape editing can expand limited geometry collections, but whether its variants improve prediction on unseen geometries, and how to allocate them across sources, require controlled evaluation. We introduce AneumoBench, a dataset and benchmark linking 401 source aneurysm geometries to 9,693 locally edited descendant records, with computational fluid dynamics (CFD) fields computed on both. It contains 80,752 steady velocity-pressure cases across eight inlet conditions and 9,715 transient sequences of velocity, pressure, and wall shear stress (WSS). Each sequence contains 100 frames sampled at 0.01-s intervals from a 1-s cardiac cycle. Mesh, point, and voxel interfaces support steady field prediction and WSS forecasting from four observed frames. With family-disjoint splits, we compare source-only training, descendant training, and descendant pretraining followed by source fine-tuning across nine architectures on 79 held-out sources. Under the reported schedules, two-stage training lowers steady-field and reset-window WSS errors relative to source-only training. With the number of sampled fields and training updates fixed within each comparison, GraphSAGE benefits from descendant training and from distributing a fixed number of descendants across more sources. For WSS, reset-window gains do not consistently persist through 96-step rollout, and lower trajectory error need not improve cycle-level shear metrics or hotspot localization. These data and protocols enable researchers to compare descendant selection and training strategies on the same unseen source geometries.

Xigui Li, Yuanye Zhou, Feiyang Xiao +16

Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China · Shanghai Academy of Artificial Intelligence for Science, Shanghai, China · Human Phenome Institute, Fudan University, Shanghai, China +1

Neural Surrogate Modeling Synthetic Data Pretraining Synthetic Data Augmentation Synthetic Benchmark Generation Computational Fluid Dynamics

Jan 20, 2025

Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions

Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contamination. Consequently, developing a reliable benchmark that effectively evaluates large language models' (LLMs) genuine capabilities in mathematical reasoning remains a critical challenge. To address these concerns, we propose RV-Bench, a novel evaluation methodology for Benchmarking LLMs with Random Variables in mathematical reasoning. Specifically, we build question-generating functions to produce random variable questions (RVQs), whose background content mirrors original benchmark problems, but with randomized variable combinations, rendering them "unseen" to LLMs. Models must completely understand the inherent question pattern to correctly answer RVQs with diverse variable combinations. Thus, an LLM's genuine reasoning capability is reflected through its accuracy and robustness on RV-Bench. We conducted extensive experiments on over 30 representative LLMs across more than 1,000 RVQs. Our findings propose that LLMs exhibit a proficiency imbalance between encountered and ``unseen'' data distributions. Furthermore, RV-Bench reveals that proficiency generalization across similar mathematical reasoning tasks is limited, but we verified it can still be effectively elicited through test-time scaling.

Zijin Hong, Hao Wu, Su Dong +8

The Hong Kong Polytechnic University, Hong Kong SAR, China · University of Electronic Science and Technology of China, Chengdu, China · Tencent Youtu Lab, Shanghai, China +2

Mathematical Reasoning Benchmarks Language Model Generalization Synthetic Benchmark Generation LLM Mathematical Reasoning

Nov 15, 2024

Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions

Large language models (LLMs) demonstrate remarkable performance across various tasks, prompting researchers to develop diverse evaluation benchmarks. However, most benchmarks typically measure the ability of LLMs to respond to individual questions, neglecting the complex interactions in real-world applications. We introduce Compound Question Synthesis (CQ-Syn) to build Compound-QA, a benchmark targeting questions composed of multiple interrelated sub-questions. This benchmark is derived from existing QA datasets, annotated with proprietary LLMs, and verified by humans for accuracy. It encompasses five categories: Factual-Statement, Cause-and-Effect, Hypothetical-Analysis, Comparison-and-Selection, and Evaluation-and-Suggestion. It evaluates the LLM capability in terms of three dimensions, including understanding, reasoning, and knowledge. Evaluating nine open-source LLMs on Compound-QA reveals that their performance on compound questions is notably lower than on non-compound questions. We further explore strategies to enhance LLMs' handling of compound questions, and our results show that these methods substantially improve models' comprehension and reasoning abilities.

Yutao Hou, Yajing Luo, Zhiwen Ruan +4

Shanghai University of Finance and Economics · Southern University of Science and Technology · University of Edinburgh +1

Multi-Hop QA LLM Evaluation Synthetic Benchmark Generation

Sep 27, 2024

HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation

Efficiently determining the satisfiability of a boolean equation -- known as the SAT problem for brevity -- is crucial in various industrial problems. Recently, the advent of deep learning methods has introduced significant potential for enhancing SAT solving. However, a major barrier to the advancement of this field has been the scarcity of large, realistic datasets. The majority of current public datasets are either randomly generated or extremely limited, containing only a few examples from unrelated problem families. These datasets are inadequate for meaningful training of deep learning methods. In light of this, researchers have started exploring generative techniques to create data that more accurately reflect SAT problems encountered in practical situations. These methods have so far suffered from either the inability to produce challenging SAT problems or time-scalability obstacles. In this paper we address both by identifying and manipulating the key contributors to a problem's ``hardness'', known as cores. Although some previous work has addressed cores, the time costs are unacceptably high due to the expense of traditional heuristic core detection techniques. We introduce a fast core detection procedure that uses a graph neural network. Our empirical results demonstrate that we can efficiently generate problems that remain hard to solve and retain key attributes of the original example problems. We show via experiment that the generated synthetic SAT problems can be used in a data augmentation setting to provide improved prediction of solver runtimes.

Joseph Cotnareanu, Zhanguang Zhang, Hui-Ling Zhen +2

McGill University Montreal, Canada · Huawei Noah’s Ark Lab Montreal, Canada · Huawei Noah’s Ark Lab Hong Kong, China +1

Synthetic Data Augmentation Synthetic Benchmark Generation Constraint Satisfaction

Jun 12, 2024

Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Framework

Existing evaluations of tabular synthesis models rely primarily on low-order statistics and downstream task performance, leaving multivariate causal relationships that go beyond pairwise correlations largely unmeasured. We argue that a systematic evaluation on high-order structural information is a crucial first step in addressing this issue in tabular data synthesis. In this paper, we present high-order structural causal information as a natural form of prior knowledge and introduce a benchmark framework to evaluate tabular synthesis models. This framework allows us to generate benchmark datasets through a flexible range of data generation processes, allowing for the training of tabular synthesis models using these datasets for further evaluation. We propose multiple benchmark tasks, high-order metrics, and causal inference tasks as downstream tasks for evaluating the quality of synthetic data generated by the trained models. Our experiments demonstrate the effectiveness of the benchmark framework in evaluating the model's ability to capture high-order structural causal information. Furthermore, our benchmarking results provide an initial assessment of state-of-the-art tabular synthesis models. These results reveal significant gaps between ideal and actual performance and highlight how baseline methods differ. We position the framework as a controlled diagnostic benchmark for causal fidelity, complementing existing low-order and downstream evaluations. We open source the benchmark framework, including both code and data along with documentation, to support further research in this area.

Zineb Senane, Axel Karlsson, Lele Cao +6

KTH Royal Institute of Technology · Stockholm, Sweden · King AI Labs, Microsoft +2

Synthetic Benchmark Generation Causal Inference Tabular Data Synthesis Synthetic Data Evaluation