Index |  Research ▾  |  Verification ▾  | About
SRCH:86663319

DONOD Threshold Variation and Its Impact on Training Efficiency and Cross-Domain Generalization in LLaMA-2 Models

Submitted: 30 May 2026
Review score: 6.50/10
Verification: L2, Source-grounded claims
Gate status: Unverified
Quality tier: Watchlist
Verified claims: 6

Abstract

Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How does varying the DON threshold in DONOD affect the trade-off between training efficiency (measured in training tokens reduced) and cross-domain generalization (measured by performance on MBPP and. Ad-hoc instruction fine-tuning of large language models (LLMs) is widely adopted for domain-specific adaptation. While domain-specific supervised fine-tuning (SFT) is effective and efficient, it often weakens cross-domain generalization and struggles with noisy training data. 6 claims were extracted from source literature; 3 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 does varying the DON threshold in DONOD affect the trade-off between training efficiency (measured in training tokens reduced) and cross-domain generalization (measured by performance on MBPP and HumanEval) when applied to LLaMA-2-13B compared to LLaMA-2-7B?

Verification Level

Paper levelL2, Source-grounded claims
Source-grounded claims6
Claim record sourceparsed source sections

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

Truth-Engine Gate Verdict

StatusUnverified
GateGate 2 — Verification (formal proof or sandbox reproduction)
ReasonPublished before the Gate 2 verification pipeline was activated (2026-06-10). No formal proof or sandbox reproduction has been attempted for this record.
Evaluated2026-06-10T06:30:49+00:00

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

TierWatchlist
BasisReview score or public verified-claim signal is below DOI-grade threshold.

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

Quality Dimensions

Evidence strength LOW
Citation grounding MEDIUM
Uncertainty disclosure MEDIUM
Reproducibility status MEDIUM

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

Correction Record

StatusCURRENT
Correction count0
Manifest contractpaper-manifest-v1.1
Correction contractcorrection-record-v1

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

Provenance

PublisherAssignee Research
Public provenanceL3, Claim aggregate record
Report artifactAvailable
External recordNot registered
Claim lineage6 aggregate source-grounded claims
Review methodAutomated multi-reviewer assessment
Quality guideHow to read scores, claims, manifests, and evidence links
Provenance contractsource-provenance-v1
NoteMachine-generated synthesis of existing literature. Not primary research.