Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence

• URL: http://arxiv.org/abs/2410.15490v3
• Date: Fri, 22 Nov 2024 20:15:01 GMT
• Title: Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence
• Authors: Norbert Tihanyi, Tamas Bisztray, Richard A. Dubniczky, Rebeka Toth, Bertalan Borsos, Bilel Cherif, Mohamed Amine Ferrag, Lajos Muzsai, Ridhi Jain, Ryan Marinelli, Lucas C. Cordeiro, Merouane Debbah, Vasileios Mavroeidis, Audun Josang,
• Abstract summary: We introduce Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models. The framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. The accompanying dataset, DIA-Bench, contains a diverse collection of challenge templates with mutable parameters presented in various formats.
• Score: 3.4049215220521933
• License:
• Abstract: As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often simplistic, allowing models to perform uniformly well and making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs that the models might memorize or guess. To address these limitations, we introduce Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying dataset, DIA-Bench, contains a diverse collection of challenge templates with mutable parameters presented in various formats, including text, PDFs, compiled binaries, visual puzzles, and CTF-style cybersecurity challenges. Our framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models' reliability. Notably, API models like GPT-4o often overestimated their mathematical capabilities, while ChatGPT-4o demonstrated better performance due to effective tool usage. In self-assessment, OpenAI's o1-mini proved to have the best judgement on what tasks it should attempt to solve. We evaluated 25 state-of-the-art LLMs using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving but also a model's adaptive intelligence and ability to assess its limitations. The dataset is publicly available on the project's page: https://github.com/DIA-Bench.

Related papers

• LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content [62.816876067499415]
  We propose LiveXiv: a scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs. We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models true abilities.
  arXiv  Detail & Related papers  (2024-10-14T17:51:23Z)
• Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models [13.532180752491954]
  We demonstrate a dramatic breakdown of function and reasoning capabilities of state-of-the-art models trained at the largest available scales. The breakdown is dramatic, as models show strong fluctuations across even slight problem variations that should not affect problem solving. We take these initial observations to stimulate urgent re-assessment of the claimed capabilities of current generation of Large Language Models.
  arXiv  Detail & Related papers  (2024-06-04T07:43:33Z)
• Combating Missing Modalities in Egocentric Videos at Test Time [92.38662956154256]
  Real-world applications often face challenges with incomplete modalities due to privacy concerns, efficiency needs, or hardware issues. We propose a novel approach to address this issue at test time without requiring retraining. MiDl represents the first self-supervised, online solution for handling missing modalities exclusively at test time.
  arXiv  Detail & Related papers  (2024-04-23T16:01:33Z)
• Improving the Capabilities of Large Language Model Based Marketing Analytics Copilots With Semantic Search And Fine-Tuning [0.9787137564521711]
  We show how a combination of semantic search, prompt engineering, and fine-tuning can be applied to dramatically improve the ability of LLMs to execute these tasks accurately. We compare both proprietary models, like GPT-4, and open-source models, like Llama-2-70b, as well as various embedding methods.
  arXiv  Detail & Related papers  (2024-04-16T03:39:16Z)
• 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)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models [23.344490944210456]
  We present 515Bench, a more challenging benchmark dataset for evaluating the problem solving abilities of large language models (LLMs) We curate challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT-Advanced exam. Our evaluation on various open-source and proprietary models reveals that the highest performance, even after using techniques like self-consistency, self-refinement and chain-of-thought prompting, is less than 40%.
  arXiv  Detail & Related papers  (2023-05-24T11:55:59Z)
• Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking [30.155625852894797]
  We propose a browser-based benchmarking tool for researchers and challenge organizers. Our tool helps test generalization capabilities of models across multiple datasets. Interactive filtering facilitates discovery of problematic behavior.
  arXiv  Detail & Related papers  (2021-10-11T11:08:35Z)
• Testing Framework for Black-box AI Models [1.916485402892365]
  In this paper, we present an end-to-end generic framework for testing AI Models. Our tool has been used for testing industrial AI models and was very effective to uncover issues.
  arXiv  Detail & Related papers  (2021-02-11T18:15:23Z)
• Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems [64.4896118325552]
  We evaluate the current state-of-the-art AES models using a model adversarial evaluation scheme and associated metrics. We find that AES models are highly overstable. Even heavy modifications(as much as 25%) with content unrelated to the topic of the questions do not decrease the score produced by the models.
  arXiv  Detail & Related papers  (2020-07-14T03:49:43Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.