paper-with-me

Papers

InstructEval: Systematic Evaluation of Instruction Selection Methods

2023-07-01 · Anirudh Ajith, Chris Pan, Mengzhou Xia, Ameet Deshpande, Karthik Narasimhan

In-context learning (ICL) performs tasks by prompting a large language model (LLM) using an instruction and a small set of annotated examples called demonstrations. Recent work has shown that precise details of the inputs used in the ICL prompt significantly impact performance, which has incentivized instruction selection algorithms. The effect of instruction-choice however is severely underexplored, with existing analyses restricted to shallow subsets of models and tasks, limiting the generalizability of their insights. We develop InstructEval, an ICL evaluation suite to conduct a thorough assessment of these techniques. The suite includes 13 open-sourced LLMs of varying scales from four model families, and covers nine tasks across three categories. Using the suite, we evaluate the relative performance of seven popular instruction selection methods over five metrics relevant to ICL. Our experiments reveal that using curated manually-written instructions or simple instructions without any task-specific descriptions often elicits superior ICL performance overall than that of automatic instruction-induction methods, pointing to a lack of generalizability among the latter. We release our evaluation suite for benchmarking instruction selection approaches and enabling more generalizable methods in this space.

📄 PDF Abstract BibTeX arXiv:2307.00259

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingIn-Context LearningLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

2025-11-13 · Huimin Ren, Yan Liang, Baiqiao Su, Chaobo Sun 외 arxiv

The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evaluating this capability remains a significa…

Instruction Following

INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models

2023-06-07 · Yew Ken Chia, Pengfei Hong, Lidong Bing, Soujanya Poria

Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master langu…

Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning

2023-07-05 · Deepanway Ghosal, Yew Ken Chia, Navonil Majumder, Soujanya Poria

Recently, the release of INSTRUCTEVAL has provided valuable insights into the performance of large language models (LLMs) that utilize encoder-decoder or decoder-only architecture. Interestingly, despite being introduced…

DecoderLanguage ModellingLarge Language Model

Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models

2024-08-04 · Yulei Qin, Yuncheng Yang, Pengcheng Guo, Gang Li 외

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not b…

One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation

2026-05-21 · Yevhen Kostiuk, Kenneth Enevoldsen arxiv

Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main problem of the instruction-based approach na…