paper-with-me

Papers

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 language but also solve complex tasks in areas like mathematics, coding, medicine, and law. Despite their impressive capabilities, there is still a lack of comprehensive understanding regarding their full potential, primarily due to the black-box nature of many models and the absence of holistic evaluation studies. To address these challenges, we present INSTRUCTEVAL, a more comprehensive evaluation suite designed specifically for instruction-tuned large language models. Unlike previous works, our evaluation involves a rigorous assessment of models based on problem-solving, writing ability, and alignment to human values. We take a holistic approach to analyze various factors affecting model performance, including the pretraining foundation, instruction-tuning data, and training methods. Our findings reveal that the quality of instruction data is the most crucial factor in scaling model performance. While open-source models demonstrate impressive writing abilities, there is substantial room for improvement in problem-solving and alignment. We are encouraged by the rapid development of models by the open-source community, but we also highlight the need for rigorous evaluation to support claims made about these models. Through INSTRUCTEVAL, we aim to foster a deeper understanding of instruction-tuned models and advancements in their capabilities. INSTRUCTEVAL is publicly available at https://github.com/declare-lab/instruct-eval.

📄 PDF Abstract BibTeX arXiv:2306.04757

Code (2)

declare-lab/instruct-eval 공식 구현
lranaldii/crossalpaca

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

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: Systematic Evaluation of Instruction Selection Methods

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

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 input…

BenchmarkingIn-Context LearningLanguage ModellingLarge Language Model

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

Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning

2023-10-20 · Lucas Weber, Elia Bruni, Dieuwke Hupkes

Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learn…

In-Context Learning

LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models

2023-06-15 · Peng Xu, Wenqi Shao, Kaipeng Zhang, Peng Gao 외

Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a compreh…

HallucinationImage CaptioningInstruction FollowingObject Hallucination+2