mlsanityData to 7 Oct 2026

TaskEval: Synthesised Evaluation for Foundation-Model Tasks

arXiv 2512.04442 ↗First posted 4 Dec 2025cs.AI cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

Hallucinations are a key concern when creating applications that rely on Foundation models (FMs). Understanding where and how these subtle failures occur in an application relies on evaluation methods known as textitevals. Prior work focuses on defining new eval methods or benchmark datasets for specific tasks. However, neither helps a software team with a task-specific FM application when there is no metric or dataset. The demand for both automated approaches and deep integration of human insight makes this a challenging problem. We address this gap by proposing an approach to synthesise a FM task-specific evaluator program that provides automation and a custom UI for capturing feedback. The core novelty of our approach lies in: (1) a task-agnostic meta-model that captures properties of any FM task, (2) an interaction protocol for efficient use of human feedback, and (3) an eval synthesiser that selects or generates an appropriate set of evals. We implement our approach in toolname and demonstrate the concept on two diverse FM tasks: chart data extraction and document question answering. A preliminary evaluation on the quality of our selected evals shows 93% and 90% accuracy respectively. Our research tackles a growing problem facing engineering teams, how to evaluate and review outputs from FM tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 4 Dec 2025.

Builds on

16 of 29 references.

References · 16

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  3. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  4. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  5. 2025Why Language Models Hallucinatecited by 205
  6. 2024Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judgescited by 197
  7. 2024Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferencescited by 142
  8. 2025Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineeringcited by 64
  9. 2025CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generationcited by 55
  10. 2024Calibration and Correctness of Language Models for Codecited by 49
  11. 2024Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verificationcited by 40
  12. 2024Large Language Models Can Self-Correct with Key Condition Verificationcited by 39
4 more
  1. 2024Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competitioncited by 16
  2. 2025Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgmentscited by 16
  3. 2024RAGProbe: An Automated Approach for Evaluating RAG Applicationscited by 7
  4. 2025Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plotscited by 7

Built on by

Not cited yet.