BenTo: Benchmark Task Reduction with In-Context Transferability

• URL: http://arxiv.org/abs/2410.13804v3
• Date: Mon, 21 Oct 2024 23:37:48 GMT
• Title: BenTo: Benchmark Task Reduction with In-Context Transferability
• Authors: Hongyu Zhao, Ming Li, Lichao Sun, Tianyi Zhou,
• Abstract summary: This paper investigates how to efficiently reduce the tasks used to benchmark large language models (LLMs) We propose a practically efficient metric for estimating the transferability between two tasks via in-context learning (ICL)
• Score: 32.561978389905434
• License:
• Abstract: Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affecting the evaluation quality. Our study reveals that task transferability and relevance provide critical information to identify the most representative subset of tasks via optimizing a facility location function. We propose a practically efficient metric for estimating the transferability between two tasks via in-context learning (ICL). By analyzing the pairwise transferability, we can reduce tasks in a modern LLM benchmark (e.g., MMLU or FLAN) to 5% while inducing only a <4% difference to the evaluation on the original benchmark. Compared to prior works, our method is training-free, gradient-free, and highly efficient requiring ICL only.

Related papers

• Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science [0.1499944454332829]
  We evaluate the classification performance of large language models (LLMs) using in-context learning (ICL) and instruction tuning (IT) ICL offers a rapid alternative for task adaptation by learning from examples without explicit gradient updates. Our research highlights the significant advantages of ICL in handling CSS tasks in few-shot settings.
  arXiv  Detail & Related papers  (2024-09-23T02:43:08Z)
• Active Testing of Large Language Model via Multi-Stage Sampling [17.89896012553348]
  AcTracer is an active testing framework tailored for large language models (LLMs) It strategically selects a small subset of test data to achieve a nearly optimal performance estimation. Our experiment results demonstrate that AcTracer achieves state-of-the-art performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-08-07T06:17:48Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• RepEval: Effective Text Evaluation with LLM Representation [55.26340302485898]
  RepEval is a metric that leverages the projection of Large Language Models (LLMs) representations for evaluation. Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.
  arXiv  Detail & Related papers  (2024-04-30T13:50:55Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• Benchmarking Causal Study to Interpret Large Language Models for Source Code [6.301373791541809]
  This paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks. We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods.
  arXiv  Detail & Related papers  (2023-08-23T20:32:12Z)
• Estimating Large Language Model Capabilities without Labeled Test Data [51.428562302037534]
  Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples. We propose the task of ICL accuracy estimation, in which we predict the accuracy of an LLM when doing in-context learning on a new task.
  arXiv  Detail & Related papers  (2023-05-24T06:55:09Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

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.