Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Learning New Facts with QLoRA: An Acquisition-Retention Frontier

Estelle Zheng, Sébastien Warichet, Emmanuel Helbert, Christophe Cerisara

Published

Aug 26, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 26, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters. We show that this assumption depends strongly on adapter capacity. We study factual acquisition in a controlled OpenStreetMap-derived benchmark where Qwen3-4B must acquire anonymized geographic associations while retaining unrelated capabilities. Comparing full fine-tuning (FFT) with quantized low-rank adaptation (QLoRA) at ranks 8, 16, 32, and 64, we find that rank induces a clear acquisition--retention frontier. Low-rank QLoRA preserves out-of-domain (OOD) performance but acquires fewer facts, whereas higher ranks improve same-fact paraphrase generalization at an increasing cost in performance on unrelated benchmarks. FFT behaves as a conservative baseline: it retains general capabilities well, but does not reach the highest factual-acquisition regime. Distributional, weight-space, and spectral diagnostics mirror this behavioral trade-off, with higher-rank QLoRA moving farther from the pretrained model. A separate math adaptation experiment shows a weaker frontier, suggesting that the effect is most pronounced when adaptation must install new factual associations rather than reinforce skills already supported by pretraining. Code and data are available at https://github.com/zhngstl/new_facts_forgetting.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Math, Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters.
  • We show that this assumption depends strongly on adapter capacity.
  • We study factual acquisition in a controlled OpenStreetMap-derived benchmark where Qwen3-4B must acquire anonymized geographic associations while retaining unrelated capabilities.

Researcher actions

  • Compare this paper against others mentioning MATH.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

MATH

Contribution summary

  • We show that this assumption depends strongly on adapter capacity.
  • We study factual acquisition in a controlled OpenStreetMap-derived benchmark where Qwen3-4B must acquire anonymized geographic associations while retaining unrelated capabilities.
  • Low-rank QLoRA preserves out-of-domain (OOD) performance but acquires fewer facts, whereas higher ranks improve same-fact paraphrase generalization at an increasing cost in performance on unrelated benchmarks.

Why it matters for eval

  • We study factual acquisition in a controlled OpenStreetMap-derived benchmark where Qwen3-4B must acquire anonymized geographic associations while retaining unrelated capabilities.
  • Low-rank QLoRA preserves out-of-domain (OOD) performance but acquires fewer facts, whereas higher ranks improve same-fact paraphrase generalization at an increasing cost in performance on unrelated benchmarks.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.