REVIEW 3 cited by
DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
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
read the original abstract
Large language models (LLMs) have achieved remarkable performance in various evaluation benchmarks. However, concerns are raised about potential data contamination in their considerable volume of training corpus. Moreover, the static nature and fixed complexity of current benchmarks may inadequately gauge the advancing capabilities of LLMs. In this paper, we introduce DyVal, a general and flexible protocol for dynamic evaluation of LLMs. Based on our framework, we build graph-informed DyVal by leveraging the structural advantage of directed acyclic graphs to dynamically generate evaluation samples with controllable complexities. DyVal generates challenging evaluation sets on reasoning tasks including mathematics, logical reasoning, and algorithm problems. We evaluate various LLMs ranging from Flan-T5-large to GPT-3.5-Turbo and GPT-4. Experiments show that LLMs perform worse in DyVal-generated evaluation samples with different complexities, highlighting the significance of dynamic evaluation. We also analyze the failure cases and results of different prompting methods. Moreover, DyVal-generated samples are not only evaluation sets, but also helpful data for fine-tuning to improve the performance of LLMs on existing benchmarks. We hope that DyVal can shed light on future evaluation research of LLMs. Code is available at: https://github.com/microsoft/promptbench.
Forward citations
Cited by 3 Pith papers
-
Automated Capability Discovery via Foundation Model Self-Exploration
ACD automatically generates thousands of open-ended tasks and clusters them into dozens of capability and failure categories, with LLM-vs-human scoring agreement (F1 = 0.86).
-
Reasoning Multimodal Large Language Model: Data Contamination and Dynamic Evaluation
A fixed-image, multi-task evaluation framework aims to detect data contamination in multimodal LLMs, but its judge is unvalidated and possibly self-referential, and the claimed harm to generalization is not supported ...
-
Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era
A tutorial proposal outlining how generative models can synthesize data across modalities for data mining, with no new research results.
Discussion (0). Continue with ORCID to comment.