Robustness of Llama-3-8B-128K Qwen-8B and Mistral-8B to Irrelevant Context Noise at 128K Scale

Abstract

Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How do Llama-3-8B-128K, Qwen-8B, and Mistral-8B differ in robustness to irrelevant context noise within the BABILong dataset as the total sequence length scales to 128K. We study the continual pretraining recipe for scaling language models' context lengths to 128K, with a focus on data engineering. We hypothesize that long context modeling, in particular textit\the ability to utilize information at arbitrary input locations\, is a capability. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 6.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do Llama-3-8B-128K, Qwen-8B, and Mistral-8B differ in robustness to irrelevant context noise within the BABILong dataset as the total sequence length scales to 128K?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance