DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
- URL: http://arxiv.org/abs/2309.17167v3
- Date: Thu, 14 Mar 2024 09:52:16 GMT
- Title: DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
- Authors: Kaijie Zhu, Jiaao Chen, Jindong Wang, Neil Zhenqiang Gong, Diyi Yang, Xing Xie,
- Abstract summary: We introduce DyVal, a protocol for dynamic evaluation of large language models (LLMs)
Based on our framework, we build graph-informed DyVal by leveraging the structural advantage of directed acyclic graphs.
We evaluate various LLMs ranging from Flan-T5-large to GPT-3.5-Turbo and GPT-4.
- Score: 112.66827096358857
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance? [1.3810901729134184]
Large Language Models (LLMs) excel at standardized tests while failing to demonstrate genuine language understanding and adaptability.
Our systematic analysis of NLP evaluation frameworks reveals pervasive vulnerabilities across the evaluation spectrum.
We lay the groundwork for new evaluation methods that resist manipulation, minimize data contamination, and assess domain-specific tasks.
arXiv Detail & Related papers (2024-12-02T20:49:21Z) - DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity.
Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data.
Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
arXiv Detail & Related papers (2024-06-25T04:27:53Z) - DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
Large Language Models (LLMs) are scalable and economical evaluators.
The question of how reliable these evaluators are has emerged as a crucial research question.
We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
arXiv Detail & Related papers (2024-05-24T08:12:30Z) - Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs [30.179703001666173]
Factuality issue is a critical concern for Large Language Models (LLMs)
We propose GraphEval to evaluate an LLM's performance using a substantially large test dataset.
Test dataset is retrieved from a large knowledge graph with more than 10 million facts without expensive human efforts.
arXiv Detail & Related papers (2024-04-01T06:01:17Z) - Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM
Evaluation [51.99752147380505]
This paper presents a benchmark self-evolving framework to dynamically evaluate Large Language Models (LLMs)
We utilize a multi-agent system to manipulate the context or question of original instances, reframing new evolving instances with high confidence.
Our framework widens performance discrepancies both between different models and within the same model across various tasks.
arXiv Detail & Related papers (2024-02-18T03:40:06Z) - F-Eval: Assessing Fundamental Abilities with Refined Evaluation Methods [102.98899881389211]
We propose F-Eval, a bilingual evaluation benchmark to evaluate the fundamental abilities, including expression, commonsense and logic.
For reference-free subjective tasks, we devise new evaluation methods, serving as alternatives to scoring by API models.
arXiv Detail & Related papers (2024-01-26T13:55:32Z) - Evaluating Large Language Models at Evaluating Instruction Following [54.49567482594617]
We introduce a challenging meta-evaluation benchmark, LLMBar, designed to test the ability of an LLM evaluator in discerning instruction-following outputs.
We discover that different evaluators exhibit distinct performance on LLMBar and even the highest-scoring ones have substantial room for improvement.
arXiv Detail & Related papers (2023-10-11T16:38:11Z) - An Examination of the Compositionality of Large Generative Vision-Language Models [7.639748270719836]
Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning.
In this paper, we examine both the evaluation metrics (VisualGPTScore, etc.) and current benchmarks for evaluating the compositionality of GVLMs.
We identify the syntactical bias in current benchmarks, which is exploited by the linguistic capability of GVLMs.
arXiv Detail & Related papers (2023-08-21T06:50:29Z)
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.