Pith. sign in

REVIEW 6 cited by

Dynamic Evaluation of Large Language Models by Meta Probing Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.14865 v2 pith:5RVVDOIQ submitted 2024-02-21 cs.CL cs.AIcs.LG

Dynamic Evaluation of Large Language Models by Meta Probing Agents

classification cs.CL cs.AIcs.LG
keywords evaluationabilitiesllmsagentsanalysisbasiclanguagemodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be easily extended to diverse scenarios. Moreover, current evaluation benchmarks can only provide the overall benchmark results and cannot support a fine-grained and multifaceted analysis of LLMs' abilities. In this paper, we propose meta probing agents (MPA), a general dynamic evaluation protocol inspired by psychometrics to evaluate LLMs. MPA is the key component of DyVal 2, which naturally extends the previous DyVal~\citep{zhu2023dyval}. MPA designs the probing and judging agents to automatically transform an original evaluation problem into a new one following psychometric theory on three basic cognitive abilities: language understanding, problem solving, and domain knowledge. These basic abilities are also dynamically configurable, allowing multifaceted analysis. We conducted extensive evaluations using MPA and found that most LLMs achieve poorer performance, indicating room for improvement. Our multifaceted analysis demonstrated the strong correlation between the basic abilities and an implicit Matthew effect on model size, i.e., larger models possess stronger correlations of the abilities. MPA can also be used as a data augmentation approach to enhance LLMs. Code is available at: https://github.com/microsoft/promptbench.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AgentReview: Exploring Peer Review Dynamics with LLM Agents

    cs.CL 2024-06 unverdicted novelty 8.0

    AgentReview is the first LLM-based simulation framework for peer review that quantifies a 37.1% decision variation attributable to reviewer biases.

  2. Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios

    cs.LG 2026-06 unverdicted novelty 7.0

    Elmes* automates fine-grained rubric construction for LLM educational evaluation via multi-agent interactions and a self-evolving SceneGen module, producing the Edu-330 benchmark that demonstrates multidimensional dif...

  3. Robust Reasoning Benchmark

    cs.LG 2026-03 unverdicted novelty 7.0

    Perturbations to math problem text cause up to 55% average accuracy drops in open-weight LLMs and sequential solving reveals context pollution in attention mechanisms.

  4. Robust Reasoning Benchmark

    cs.LG 2026-03 unverdicted novelty 7.0

    The Robust Reasoning Benchmark shows frontier LLMs are mostly resilient to textual perturbations on AIME problems while open-weight models suffer up to 54% accuracy drops and exhibit accuracy decay on later problems d...

  5. Benchmark Data Contamination of Large Language Models: A Survey

    cs.CL 2024-06 unverdicted novelty 3.0

    A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.

  6. The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey

    cs.AI 2024-04 unverdicted novelty 3.0

    A survey of emerging AI agent architectures that organizes single and multi-agent designs around reasoning, planning, tool use, communication, and reflection phases.