AutoBencher: Towards Declarative Benchmark Construction

• URL: http://arxiv.org/abs/2407.08351v2
• Date: Fri, 28 Feb 2025 08:14:49 GMT
• Title: AutoBencher: Towards Declarative Benchmark Construction
• Authors: Xiang Lisa Li, Farzaan Kaiyom, Evan Zheran Liu, Yifan Mai, Percy Liang, Tatsunori Hashimoto,
• Abstract summary: We use AutoBencher to create datasets for math, multilinguality, knowledge, and safety.<n>The scalability of AutoBencher allows it to test fine-grained categories knowledge, creating datasets that elicit 22% more model errors (i.e., difficulty) than existing benchmarks.
• Score: 74.54640925146289
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present AutoBencher, a declarative framework for automatic benchmark construction, and use it to scalably discover novel insights and vulnerabilities of existing language models. Concretely, given a few desiderata of benchmarks (e.g., question difficulty, topic salience), we operationalize each desideratum and cast benchmark creation as an optimization problem. Specifically, we experiment with two settings with different optimization objectives: (i) for capability evaluation, we declare the goal of finding a salient, difficult dataset that induces novel performance patterns; (ii) for safety evaluation, we declare the goal of finding a dataset of unsafe prompts that existing LMs fail to decline. To tackle this optimization problem, we use a language model to iteratively propose and refine dataset descriptions, which are then used to generate topic-specific questions and answers. These descriptions are optimized to improve the declared desiderata. We use AutoBencher (powered by GPT-4) to create datasets for math, multilinguality, knowledge, and safety. The scalability of AutoBencher allows it to test fine-grained categories and tail knowledge, creating datasets that elicit 22% more model errors (i.e., difficulty) than existing benchmarks. On the novelty ends, AutoBencher also helps identify specific gaps not captured by existing benchmarks: e.g., Gemini-Pro has knowledge gaps on Permian Extinction and Fordism while GPT-4o fails to decline harmful requests about cryptocurrency scams.

Related papers

• Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models [24.481028155002523]
  We present Zero-shot Benchmarking (ZSB), a framework for creating high-quality benchmarks for any task. ZSB is simple and flexible: it requires only the creation of a prompt for data generation and one for evaluation. It is scalable to tasks and languages where collecting real-world data is costly or impractical.
  arXiv  Detail & Related papers  (2025-04-01T17:40:08Z)
• TVBench: Redesigning Video-Language Evaluation [48.71203934876828]
  We show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning. We propose TVBench, a novel open-source video multiple-choice question-answering benchmark.
  arXiv  Detail & Related papers  (2024-10-10T09:28:36Z)
• An Evaluation Framework for Attributed Information Retrieval using Large Language Models [5.216296688442701]
  We propose a framework to evaluate and benchmark attributed information seeking. Experiments using HAGRID, an attributed information-seeking dataset, show the impact of different scenarios on the correctness and attributability of answers.
  arXiv  Detail & Related papers  (2024-09-12T12:57:08Z)
• Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction [10.428174043080622]
  Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. We propose SWiM, an evaluation framework that addresses the limitations of standard tests. We also propose medoid voting, a simple, but effective training-free approach that helps alleviate this effect.
  arXiv  Detail & Related papers  (2024-07-04T05:46:20Z)
• Prompt Stability Scoring for Text Annotation with Large Language Models [0.0]
  Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set of instructions. The diagnose of LM outputs may nonetheless be vulnerable to small changes in the prompt design.
  arXiv  Detail & Related papers  (2024-07-02T08:11:18Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests. First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics. Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation [65.16137964758612]
  We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text.
  arXiv  Detail & Related papers  (2024-05-31T20:15:10Z)
• MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis [1.5761916307614148]
  We propose the first benchmark of sentence embeddings for French. We compare 51 carefully selected embedding models on a large scale. We find that even if no model is the best on all tasks, large multilingual models pre-trained on sentence similarity perform exceptionally well.
  arXiv  Detail & Related papers  (2024-05-30T20:34:37Z)
• Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation [9.80836683456026]
  We tackle data-to-text for isiXhosa, which is low-resource and agglutinative. We introduce Triples-to-isiXhosa (T2X), a new dataset based on a subset of WebNLG. We develop an evaluation framework for T2X that measures how accurately generated text describes the data.
  arXiv  Detail & Related papers  (2024-03-12T11:53:27Z)
• Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models [81.27391252152199]
  Large language models (LLMs) have achieved impressive performance across various natural language benchmarks. We propose to automate dataset updating and provide systematic analysis regarding its effectiveness. There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, and 2) extending strategy that further expands existing samples.
  arXiv  Detail & Related papers  (2024-02-19T07:15:59Z)
• Enhancing Retrieval Processes for Language Generation with Augmented Queries [0.0]
  This research focuses on addressing this issue through Retrieval-Augmented Generation (RAG), a technique that guides models to give accurate responses based on real facts. To overcome scalability issues, the study explores connecting user queries with sophisticated language models such as BERT and Orca2. The empirical results indicate a significant improvement in the initial language model's performance under RAG.
  arXiv  Detail & Related papers  (2024-02-06T13:19:53Z)
• Automatic Evaluation of Attribution by Large Language Models [24.443271739599194]
  We investigate the automatic evaluation of attribution given by large language models (LLMs) We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing.
  arXiv  Detail & Related papers  (2023-05-10T16:58:33Z)
• GEMv2: Multilingual NLG Benchmarking in a Single Line of Code [161.1761414080574]
  Generation, Evaluation, and Metrics Benchmark introduces a modular infrastructure for dataset, model, and metric developers. GEMv2 supports 40 documented datasets in 51 languages. Models for all datasets can be evaluated online and our interactive data card creation and rendering tools make it easier to add new datasets to the living benchmark.
  arXiv  Detail & Related papers  (2022-06-22T17:52:30Z)
• ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models [102.63817106363597]
  We build ELEVATER, the first benchmark to compare and evaluate pre-trained language-augmented visual models. It consists of 20 image classification datasets and 35 object detection datasets, each of which is augmented with external knowledge. We will release our toolkit and evaluation platforms for the research community.
  arXiv  Detail & Related papers  (2022-04-19T10:23:42Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)
• 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)

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.