Specification Overfitting in Artificial Intelligence

• URL: http://arxiv.org/abs/2403.08425v3
• Date: Thu, 02 Jan 2025 21:45:02 GMT
• Title: Specification Overfitting in Artificial Intelligence
• Abstract summary: Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency.<n>High-level requirements such as fairness and robustness need to be formalized into concrete specification metrics.<n>This paper defines specification overfitting, a scenario where systems focus excessively on specified metrics to the detriment of high-level requirements and task performance.
• Score: 1.8292622558116727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency. Consequently, regulatory bodies struggle with containing this technology's potential negative side effects. High-level requirements such as fairness and robustness need to be formalized into concrete specification metrics, imperfect proxies that capture isolated aspects of the underlying requirements. Given possible trade-offs between different metrics and their vulnerability to over-optimization, integrating specification metrics in system development processes is not trivial. This paper defines specification overfitting, a scenario where systems focus excessively on specified metrics to the detriment of high-level requirements and task performance. We present an extensive literature survey to categorize how researchers propose, measure, and optimize specification metrics in several AI fields (e.g., natural language processing, computer vision, reinforcement learning). Using a keyword-based search on papers from major AI conferences and journals between 2018 and mid-2023, we identify and analyze 74 papers that propose or optimize specification metrics. We find that although most papers implicitly address specification overfitting (e.g., by reporting more than one specification metric), they rarely discuss which role specification metrics should play in system development or explicitly define the scope and assumptions behind metric formulations.

Related papers

• RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level [0.0]
  Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring.<n>The available readiness frameworks are heterogeneous and difficult to apply automatically.<n>This paper makes two contributions: first, we unify these three frameworks into the Unified AI Readiness Level (AIRL), a nine-level scale built on an environmental evidence ladder.<n>Second, we propose RAIL, a panel-of-experts classifier that operationalizes the scale.
  arXiv  Detail & Related papers  (2026-08-13T16:17:41Z)
• InSPECtor: Improving SLEIGH Processor Specification Veracity via Proxy [14.535794931718229]
  This study is a significant undertaking to enable the systematic validation of open-source SLEIGH language specifications.<n>We design and implement a testing framework based on an automated oracle validation strategy by proxy.<n>Applying InSPECtor across diverse, open-source specifications, we uncovered over 38,920 discrepancies that led to 125 unique bugs.
  arXiv  Detail & Related papers  (2026-08-13T10:08:41Z)
• Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents [7.228124845671868]
  Agentic AI systems can now generate code with remarkable fluency.<n>But a fundamental question remains: emphdoes the generated code actually do what the user intended?
  arXiv  Detail & Related papers  (2026-03-17T21:28:59Z)
• Is your AI Model Accurate Enough? The Difficult Choices Behind Rigorous AI Development and the EU AI Act [11.9330079062021]
  The 2024 European Union AI Act mandates an "appropriate level of accuracy" for high-risk systems.<n>This paper provides a legal-technical analysis of the choices that shape how accuracy is defined, measured, and assessed.<n>By making the techno-normative dimensions of accuracy explicit, this paper contributes to broader interdisciplinary debates on AI governance and regulation.
  arXiv  Detail & Related papers  (2026-03-11T15:51:37Z)
• From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs [65.04549036809557]
  We introduce a benchmark built from pedestrian-perspective videos captured with synchronized stereo cameras, LiDAR, and IMU/GPS sensors.<n>This dataset provides metrically precise 3D information, enabling the automatic generation of spatial reasoning questions.<n> Evaluations reveal that the performance gains observed in structured indoor benchmarks vanish in open-world settings.
  arXiv  Detail & Related papers  (2025-12-22T18:58:12Z)
• ELAIPBench: A Benchmark for Expert-Level Artificial Intelligence Paper Understanding [49.67493845115009]
  ELAIPBench is a benchmark curated by domain experts to evaluate large language models' comprehension of AI research papers.<n>It spans three difficulty levels and emphasizes non-trivial reasoning rather than shallow retrieval.<n>Experiments show that the best-performing LLM achieves an accuracy of only 39.95%, far below human performance.
  arXiv  Detail & Related papers  (2025-10-12T11:11:20Z)
• AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios [51.46347732659174]
  Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications.<n>AgentIF is the first benchmark for systematically evaluating LLM instruction following ability in agentic scenarios.
  arXiv  Detail & Related papers  (2025-05-22T17:31:10Z)
• Requirements-Driven Automated Software Testing: A Systematic Review [12.953746641112518]
  This systematic literature review critically examines the current state of requirements input formats, transformation techniques, generated test artifacts, evaluation methods, and prevailing limitations.<n>Our findings highlight the predominance of functional requirements, model-based specifications, and natural language formats.<n>Most existing frameworks are sequential and dependent on singular intermediate representations, and while test cases, structured textual formats, and requirements coverage are common, full automation remains rare.
  arXiv  Detail & Related papers  (2025-02-25T23:13:09Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• Pushing the Boundary: Specialising Deep Configuration Performance Learning [0.0]
  This thesis begins with a systematic literature review of deep learning techniques in configuration performance modeling. The first knowledge gap is the lack of understanding about which encoding scheme is better. The second knowledge gap is the sparsity inherited from the configuration landscape.
  arXiv  Detail & Related papers  (2024-07-02T22:59:19Z)
• Is Reference Necessary in the Evaluation of NLG Systems? When and Where? [58.52957222172377]
  We show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.
  arXiv  Detail & Related papers  (2024-03-21T10:31:11Z)
• Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets [92.38654521870444]
  We introduce ACES, a contrastive challenge set spanning 146 language pairs. This dataset aims to discover whether metrics can identify 68 translation accuracy errors. We conduct a large-scale study by benchmarking ACES on 50 metrics submitted to the WMT 2022 and 2023 metrics shared tasks.
  arXiv  Detail & Related papers  (2024-01-29T17:17:42Z)
• PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models [72.57329554067195]
  ProxyQA is an innovative framework dedicated to assessing longtext generation. It comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. It assesses the generated content's quality through the evaluator's accuracy in addressing the proxy-questions.
  arXiv  Detail & Related papers  (2024-01-26T18:12:25Z)
• Towards a Responsible AI Metrics Catalogue: A Collection of Metrics for AI Accountability [28.67753149592534]
  This study bridges the accountability gap by introducing our effort towards a comprehensive metrics catalogue. Our catalogue delineates process metrics that underpin procedural integrity, resource metrics that provide necessary tools and frameworks, and product metrics that reflect the outputs of AI systems.
  arXiv  Detail & Related papers  (2023-11-22T04:43:16Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Truthful Meta-Explanations for Local Interpretability of Machine Learning Models [10.342433824178825]
  We present a local meta-explanation technique which builds on top of the truthfulness metric, which is a faithfulness-based metric. We demonstrate the effectiveness of both the technique and the metric by concretely defining all the concepts and through experimentation.
  arXiv  Detail & Related papers  (2022-12-07T08:32:04Z)
• Metrics reloaded: Recommendations for image analysis validation [59.60445111432934]
  Metrics Reloaded is a comprehensive framework guiding researchers in the problem-aware selection of metrics. The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics.
  arXiv  Detail & Related papers  (2022-06-03T15:56:51Z)
• Bias and unfairness in machine learning models: a systematic literature review [43.55994393060723]
  This study aims to examine existing knowledge on bias and unfairness in Machine Learning models. A Systematic Literature Review found 40 eligible articles published between 2017 and 2022 in the Scopus, IEEE Xplore, Web of Science, and Google Scholar knowledge bases.
  arXiv  Detail & Related papers  (2022-02-16T16:27:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.