Papers
arxiv:2404.02060

Long-context LLMs Struggle with Long In-context Learning

Published on Apr 2
· Featured in Daily Papers on Apr 3
Authors:
,
,
,

Abstract

Large Language Models (LLMs) have made significant strides in handling long sequences exceeding 32K tokens. However, their performance evaluation has largely been confined to metrics like perplexity and synthetic tasks, which may not fully capture their abilities in more nuanced, real-world scenarios. This study introduces a specialized benchmark (LIConBench) focusing on long in-context learning within the realm of extreme-label classification. We meticulously selected six datasets with a label range spanning 28 to 174 classes covering different input (few-shot demonstration) length from 2K to 50K. Our benchmark requires LLMs to comprehend the entire input to recognize the massive label spaces to make correct prediction. We evaluate 13 long-context LLMs on our benchmarks. We find that the long-context LLMs perform relatively well under the token length of 20K and the performance benefits from utilizing the long context window. However, after the context window exceeds 20K, most LLMs except GPT-4 will dip dramatically. This suggests a notable gap in current LLM capabilities for processing and understanding long, context-rich sequences. Further analysis revealed a tendency among models to favor predictions for labels presented towards the end at the sequence. Their ability to reason over multiple pieces in the long sequence is yet to be improved. Our study reveals that long context understanding and reasoning is still a challenging task for the existing LLMs. We believe LIConBench could serve as a more realistic evaluation for the future long context LLMs.

Community

This would have become the new "Lost in the Middle" if:
a) The writing was a little clearer (GPT-4 could help here!)
b) Some of the experiments were either better designed or better explained (why were multiple rounds used as the context window grew? that mitigated the effect, no?)
c) Gemini 1.5 was in the mix

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Thank you for your wonderful work! I would love to see Claude3 models evaluated here as well! Haiku is very affordable and has a 200k context window.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2404.02060 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 1

Collections including this paper 24