Large Language Models Can be Lazy Learners: Analyze Shortcuts in
In-Context Learning
- URL: http://arxiv.org/abs/2305.17256v2
- Date: Sat, 9 Sep 2023 18:32:00 GMT
- Title: Large Language Models Can be Lazy Learners: Analyze Shortcuts in
In-Context Learning
- Authors: Ruixiang Tang, Dehan Kong, Longtao Huang, Hui Xue
- Abstract summary: Large language models (LLMs) have recently shown great potential for in-context learning.
This paper investigates the reliance of LLMs on shortcuts or spurious correlations within prompts.
We uncover a surprising finding that larger models are more likely to utilize shortcuts in prompts during inference.
- Score: 28.162661418161466
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) have recently shown great potential for
in-context learning, where LLMs learn a new task simply by conditioning on a
few input-label pairs (prompts). Despite their potential, our understanding of
the factors influencing end-task performance and the robustness of in-context
learning remains limited. This paper aims to bridge this knowledge gap by
investigating the reliance of LLMs on shortcuts or spurious correlations within
prompts. Through comprehensive experiments on classification and extraction
tasks, we reveal that LLMs are "lazy learners" that tend to exploit shortcuts
in prompts for downstream tasks. Additionally, we uncover a surprising finding
that larger models are more likely to utilize shortcuts in prompts during
inference. Our findings provide a new perspective on evaluating robustness in
in-context learning and pose new challenges for detecting and mitigating the
use of shortcuts in prompts.
Related papers
- Shortcut Learning in In-Context Learning: A Survey [17.19214732926589]
Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks.
This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL)
arXiv Detail & Related papers (2024-11-04T12:13:04Z) - Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models [9.854718405054589]
Large Language Models (LLMs) have shown remarkable capabilities in various natural language processing tasks.
This paper presents Shortcut Suite, a test suite designed to evaluate the impact of shortcuts on LLMs' performance.
arXiv Detail & Related papers (2024-10-17T08:52:52Z) - Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut
Learning in Text Classification by Language Models [20.70050968223901]
This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model reliability beyond oversimplified shortcuts.
We introduce a comprehensive benchmark that categorizes shortcuts into occurrence, style, and concept.
Our research systematically investigates models' resilience and susceptibilities to sophisticated shortcuts.
arXiv Detail & Related papers (2024-09-26T01:17:42Z) - C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations.
Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
arXiv Detail & Related papers (2024-02-17T11:28:08Z) - Rethinking Interpretability in the Era of Large Language Models [76.1947554386879]
Large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks.
The capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human.
These new capabilities raise new challenges, such as hallucinated explanations and immense computational costs.
arXiv Detail & Related papers (2024-01-30T17:38:54Z) - Learning Shortcuts: On the Misleading Promise of NLU in Language Models [4.8951183832371]
Large language models (LLMs) have enabled significant performance gains in the field of natural language processing.
Recent studies have found that LLMs often resort to shortcuts when performing tasks, creating an illusion of enhanced performance while lacking generalizability in their decision rules.
arXiv Detail & Related papers (2024-01-17T21:55:15Z) - INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning [59.07490387145391]
Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks.
Their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language.
We introduce a novel instruction tuning dataset, INTERS, encompassing 20 tasks across three fundamental IR categories.
arXiv Detail & Related papers (2024-01-12T12:10:28Z) - Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored.
We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
arXiv Detail & Related papers (2023-12-26T07:24:46Z) - Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools.
Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions.
Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
arXiv Detail & Related papers (2023-09-20T09:23:46Z) - Shortcut Learning of Large Language Models in Natural Language
Understanding [119.45683008451698]
Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks.
They might rely on dataset bias and artifacts as shortcuts for prediction.
This has significantly affected their generalizability and adversarial robustness.
arXiv Detail & Related papers (2022-08-25T03:51:39Z)
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.