EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees

• URL: http://arxiv.org/abs/2503.08893v2
• Date: Fri, 11 Jul 2025 05:27:37 GMT
• Title: EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
• Authors: Zhiyuan Zeng, Yizhong Wang, Hannaneh Hajishirzi, Pang Wei Koh,
• Abstract summary: We develop a weakness profiling method for language model evaluations.<n>EvalTree identifies weaknesses more precisely and comprehensively.<n>We show how EvalTree exposes flaws in Arenas human-based evaluation practice.
• Score: 69.96560215277285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An ideal model evaluation should achieve two goals: identifying where the model fails and providing actionable improvement guidance. Toward these goals for language model (LM) evaluations, we formulate the problem of generating a weakness profile, a set of weaknesses expressed in natural language, given an LM's performance on every individual instance in a benchmark. We introduce a suite of quantitative assessments to compare different weakness profiling methods. We also introduce a weakness profiling method EvalTree. EvalTree constructs a capability tree where each node represents a capability described in natural language and is linked to a subset of benchmark instances that specifically evaluate this capability; it then extracts nodes where the LM performs poorly to generate a weakness profile. On the MATH and WildChat benchmarks, we show that EvalTree outperforms baseline weakness profiling methods by identifying weaknesses more precisely and comprehensively. Weakness profiling further enables weakness-guided data collection, and training data collection guided by EvalTree-identified weaknesses improves LM performance more than other data collection strategies. We also show how EvalTree exposes flaws in Chatbot Arena's human-voter-based evaluation practice. To facilitate future work, we provide an interface that allows practitioners to interactively explore the capability trees built by EvalTree.

Related papers

• SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation [70.27631454256024]
  SkillVerse is an unsupervised tree-structured diagnosis framework for understanding model proficiency in specific abilities.<n>Given proficiency at arbitrary levels of granularity, SkillVerse is flexible to produce insights of behaviors of modern large models.
  arXiv  Detail & Related papers  (2025-05-31T00:08:59Z)
• Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution [66.11004226578771]
  Existing robust benchmark datasets have two key limitations. They generate only a limited range of perturbations for a single Information Extraction (IE) task. Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench. We show that training with only textbf15% of the data leads to an average textbf7.5% relative performance improvement across three IE tasks.
  arXiv  Detail & Related papers  (2025-03-05T05:39:29Z)
• xIDS-EnsembleGuard: An Explainable Ensemble Learning-based Intrusion Detection System [7.2738577621227085]
  We focus on addressing the challenges of detecting malicious attacks in networks by designing an advanced Explainable Intrusion Detection System (xIDS)<n>Existing machine learning and deep learning approaches have invisible limitations, such as potential biases in predictions, a lack of interpretability, and the risk of overfitting to training data.<n>We propose an ensemble learning technique called "EnsembleGuard" to overcome these challenges.
  arXiv  Detail & Related papers  (2025-03-01T20:49:31Z)
• Beyond the Singular: The Essential Role of Multiple Generations in Effective Benchmark Evaluation and Analysis [10.133537818749291]
  Large language models (LLMs) have demonstrated significant utilities in real-world applications.<n> Benchmark evaluations are crucial for assessing the capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-02-13T03:43:33Z)
• Ranking Perspective for Tree-based Methods with Applications to Symbolic Feature Selection [3.2964064859807496]
  Tree-based methods are powerful nonparametric techniques in statistics and machine learning. Recent applications have revealed their surprising ability to distinguish transformations that remain obscure under current theoretical understanding. This work provides a finite-sample analysis of tree-based methods from a ranking perspective.
  arXiv  Detail & Related papers  (2024-10-03T16:03:39Z)
• UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs [19.097842830790405]
  Existing benchmarks for summarization quality evaluation often lack diverse input scenarios and focus on narrowly defined dimensions. We create UniSumEval benchmark, which extends the range of input context and provides fine-grained, multi-dimensional annotations.
  arXiv  Detail & Related papers  (2024-09-30T02:56:35Z)
• Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning [53.241569810013836]
  We propose a novel framework that utilizes large language models (LLMs) to identify effective feature generation rules. We use decision trees to convey this reasoning information, as they can be easily represented in natural language. OCTree consistently enhances the performance of various prediction models across diverse benchmarks.
  arXiv  Detail & Related papers  (2024-06-12T08:31:34Z)
• Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations [111.88727295707454]
  This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts. We conduct experiments on pre-trained language models for analysis and evaluation of OOD robustness.
  arXiv  Detail & Related papers  (2023-06-07T17:47:03Z)
• From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework [91.94389491920309]
  Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. We set up a unified automatic robustness evaluation framework, shifting towards model-centric evaluation to exploit the advantages of adversarial attacks.
  arXiv  Detail & Related papers  (2023-05-29T14:55:20Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [86.02610674750345]
  Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations. All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
  arXiv  Detail & Related papers  (2021-11-04T12:59:55Z)
• Unsupervised Learning of Explainable Parse Trees for Improved Generalisation [15.576061447736057]
  We propose an attention mechanism over Tree-LSTMs to learn more meaningful and explainable parse tree structures. We also demonstrate the superior performance of our proposed model on natural language inference, semantic relatedness, and sentiment analysis tasks.
  arXiv  Detail & Related papers  (2021-04-11T12:10:03Z)
• Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach [78.77265671634454]
  We make use of a multi-task objective, i.e., the models simultaneously predict words as well as ground truth parse trees in a form called "syntactic distances" Experimental results on the Penn Treebank and Chinese Treebank datasets show that when ground truth parse trees are provided as additional training signals, the model is able to achieve lower perplexity and induce trees with better quality.
  arXiv  Detail & Related papers  (2020-05-12T15:35:00Z)
• Feature Partitioning for Robust Tree Ensembles and their Certification in Adversarial Scenarios [8.300942601020266]
  We focus on evasion attacks, where a model is trained in a safe environment and exposed to attacks at test time. We propose a model-agnostic strategy that builds a robust ensemble by training its basic models on feature-based partitions of the given dataset. Our algorithm guarantees that the majority of the models in the ensemble cannot be affected by the attacker.
  arXiv  Detail & Related papers  (2020-04-07T12:00:40Z)

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.