Amazon's StalePO: the translation model that improved most on MQM scored worst on COMET, chrF and BLEU

Amazon's Translation Services team reported on 14 September 2026 that fine-tuning GPT-OSS 120B on post-edits of an older MT system, with an objective it calls StalePO, raised the share of English-to-Hindi segments passing all seven MQM checks by 14.9 points (13.8 under professional translators). The same model scored worst of eight systems on COMET, chrF and BLEU against those post-edits. Across the eight, COMET and the MQM gain rank in opposite order (Spearman -0.71, our calculation). Plain supervised fine-tuning on the post-edits raised BLEU by 8.4 and the pass rate by 1.8.
What Amazon published on 14 September 2026
arXiv:2609.16340, by Rohit Dhaipule, Sukhdeep Singh Kharbanda, Prasanth Bathala, Pradyumna Lanka and Anubhav Shrimal of Translation Services at Amazon, names a problem every localization program with a translation memory has: the only preference data available is human post-edits of the previous engine. Post-editing is priced per segment, so nobody re-edits millions of segments each time the model is replaced. The authors call this the stale preference problem.
The setup: GPT-OSS 120B with QLoRA (rank 8) on 8 A100s. English to Hindi uses 24k training post-edits, filtered by a Kimi K2.5 classifier to keep edits that modernise style (formal Sanskrit-derived vocabulary to the conversational transliterations the style guide mandates, passive to active) and fix punctuation. English to Turkish uses 10k unfiltered post-edits. The source prompt carries the target-language style guide and termbase entries. Evaluation is on temporally disjoint 5,000-segment test sets, scored by seven binary LLM judges built on Claude Sonnet 4.5 (Verity, Design, Terminology, Locale Convention, Style, Accuracy, Fluency), with professional translators re-annotating 2,000 Hindi segments (24,446 words).
Headline: +14.9 pp all-pass on English to Hindi, +4.6 pp on English to Turkish, +13.8 pp under human MQM on Hindi. Turkish has no human evaluation.
The better the MQM result, the worse the reference-based score
| Method | Style | Accuracy | Fluency | All-pass | TER (lower better) | COMET | chrF | BLEU | Source |
|---|---|---|---|---|---|---|---|---|---|
| Base (GPT-OSS 120B) | 0 | 0 | 0 | 0 | 51.57 | 83.59 | 55.60 | 37.41 | Tables 1, 4 |
| SFT on post-edits | +2.0 | +1.5 | +12.1 | +1.8 | 50.18 | 83.65 | 59.66 | 45.82 | Tables 1, 4 |
| DPO | +1.0 | -0.3 | +0.7 | -0.4 | 50.35 | 83.83 | 56.35 | 39.07 | Tables 1, 4 |
| TDPO | +1.4 | +0.5 | +1.8 | +0.5 | 50.51 | 83.90 | 56.15 | 38.59 | Tables 1, 4 |
| APO-Down | +2.3 | -1.2 | +0.2 | +0.6 | 50.51 | 83.70 | 56.01 | 38.94 | Tables 1, 4 |
| BAPO | +1.2 | -0.4 | +0.9 | -0.2 | 50.41 | 83.84 | 56.08 | 39.05 | Tables 1, 4 |
| BAPO-Down | +15.4 | -6.4 | +16.9 | +7.4 | 56.79 | 83.10 | 52.34 | 41.04 | Tables 1, 4 |
| StalePO | +20.9 | -5.4 | +16.5 | +14.9 | 53.52 | 82.86 | 52.19 | 36.37 | Tables 1, 4 |
We ranked the eight systems (base plus seven methods) on each reference-based metric and on the all-pass change. Spearman's rho against the all-pass change is -0.71 for COMET (p = 0.047), -0.54 for TER (sign flipped so higher is better), -0.52 for chrF and -0.07 for BLEU. Eight points is a small sample, so read the direction, not the decimals: none of the four metrics ranks the systems the way the MQM judges and the human annotators do.
The paper's own explanation is Appendix A. On the 24,220 Hindi training segments, post-edits are closer to the legacy NMT output (mean TER 0.426) than to the new model (0.517), and closer to the legacy output in 55.3% of segments against 23.7%. Post-editors correct; they do not retranslate. Score a new model against those edits and you reward it for sounding like the old engine. The example the authors give: the style guide mandates एंटर for "enter", the post-edit kept the formal दर्ज, and the reference metrics penalise the correct choice.
StalePO is not free. Accuracy falls 5.4 pp under the LLM judge and 3.5 pp under humans, and the human breakdown puts most of it in minor untranslated spans; mistranslations and omissions are "nearly unchanged". Terminology drops 2.0 pp under the judge and rises 0.8 under humans.
Three constraints turn stale post-edits into a gain, and each one alone does nothing
Standard DPO only asks that the preferred response gain likelihood relative to the dispreferred one. When the preferred response, the post-edit, is worse than what the model already writes, DPO can raise its likelihood and pull the model backwards. StalePO combines three fixes from earlier work: downward control from APO-Down (both likelihoods must fall), an anchor to the model's own sampled base output from BAPO, and a token-level KL from TDPO.
The ablation is the most useful table in the paper for a practitioner. DPO tuned on its own sweep moves the pass rate by -0.4 pp, TDPO +0.5, BAPO -0.2, APO-Down +0.6: none moves the pass rate by as much as one point. Down plus anchor (BAPO-Down) reaches +7.4. Adding the token-level KL doubles it to +14.9 and recovers a point of accuracy. On the hyperparameters, all-pass peaks at KL coefficient α = 0.25, and without the anchor every metric stays near the base.
If you own a post-edit archive, stop scoring new engines against it
Your translation memory is a biased reference set. Any engine evaluation that uses post-edits of the incumbent engine as references will favour the incumbent and its imitators. In this paper that bias is large enough to invert the ranking. Use reference-free, category-level MQM (human or judged) for engine selection, and keep COMET or BLEU against post-edits only as a regression alarm.
Do not fine-tune on the archive with SFT and call it adaptation. SFT raised BLEU by 8.4 and the pass rate by 1.8, and it lowered terminology by 3.3 pp. It learns the old engine's scaffolding along with the edits.
Filter by what changed, not by volume. The Hindi gain (+14.9) came from 24k edits selected for one kind of change; the unfiltered Turkish set (10k) gave +4.6 on a stronger base. The paper cannot separate the filter's effect from the language's, but a classifier that tags edits by MQM category is cheap next to a new round of post-editing.
Expect an accuracy cost and budget review for it. A model pushed toward conversational style oversimplifies. Route the untranslated-span errors to a human check before release.
A judgement, marked as one: the paper's numbers are relative to an undisclosed base pass rate, the Turkish result has no human check, and the method is from a single company's data. It is still the clearest published evidence that a localization archive's value lies in which categories the editor fixed, which is exactly the metadata most archives never record.
Check it yourself
# Rank correlation between each reference metric and the MQM all-pass change
# (values copied from arXiv:2609.16340 Table 1 and Table 4, English to Hindi)
python3 - <<'EOF'
from scipy.stats import spearmanr
ap = [0, 1.8, -0.4, 0.5, 0.6, -0.2, 7.4, 14.9] # Base SFT DPO TDPO APO-Down BAPO BAPO-Down StalePO
ter = [51.57, 50.18, 50.35, 50.51, 50.51, 50.41, 56.79, 53.52]
comet = [83.59, 83.65, 83.83, 83.90, 83.70, 83.84, 83.10, 82.86]
chrf = [55.60, 59.66, 56.35, 56.15, 56.01, 56.08, 52.34, 52.19]
bleu = [37.41, 45.82, 39.07, 38.59, 38.94, 39.05, 41.04, 36.37]
for n, v in [("TER", [-x for x in ter]), ("COMET", comet), ("chrF", chrf), ("BLEU", bleu)]:
r = spearmanr(v, ap); print(n, round(r.correlation, 3), round(r.pvalue, 3))
EOF
# TER -0.539 0.168
# COMET -0.714 0.047
# chrF -0.524 0.183
# BLEU -0.071 0.867
To test the incumbent bias on your own archive, compute TER from each post-edit to the legacy output and to the candidate engine's output, as in the paper's Appendix A. With sacrebleu: TER().sentence_score(pe, [legacy]).score against TER().sentence_score(pe, [candidate]).score, then count how often the legacy distance is smaller. If it is smaller in most segments, your references are measuring resemblance to the old engine. The paper is at https://arxiv.org/pdf/2609.16340; Table 1 is on page 5, Tables 3 and 4 in Appendix A.
What would prove this wrong
The claim is that reference-based metrics computed against post-edits of an older engine rank newer systems in the wrong order. It is wrong if an independent replication on a public post-edit corpus (for example the WMT or QE shared-task post-edit sets) finds a positive rank correlation, rho above +0.5, between COMET against post-edits and human MQM pass rates across at least six systems trained on those post-edits. We will look for one in the WMT 2026 proceedings and on arXiv by 30 June 2027.
Narrower: if a human MQM evaluation of the English to Turkish StalePO model is published and shows no all-pass gain, the method's +4.6 pp on an unfiltered set was a judge artefact, and the "filter by what changed" advice becomes a requirement rather than a recommendation.
Sources
- Rohit Dhaipule, Sukhdeep Singh Kharbanda, Prasanth Bathala, Pradyumna Lanka, Anubhav Shrimal (Translation Services, Amazon), StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation, arXiv:2609.16340v1, 14 September 2026. Tables 1 to 4, Sections 2, 5, 6, Limitations, Appendix A.
- Karel D'Oosterlinck et al., Anchored Preference Optimization and Contrastive Revisions, TACL 2025 (APO-Down).
- Rafael Rafailov et al., Direct Preference Optimization: Your Language Model is Secretly a Reward Model, NeurIPS 2023.
- Arle Lommel et al., Multidimensional Quality Metrics (MQM) definition, QTLaunchPad, 2014.
Related BLOMEGA guides: COMETKiwi on real localisation post-edits (LocQE) · LLM judges rank machines above human translators · WMT 2026 terminology and glossary adherence
FAQ
What is the stale preference problem in machine translation?
Preference data for a new MT model is usually human post-edits of an older engine's output, because re-editing for every new model is too expensive. Those post-edits keep the old engine's wording, so they are better than the new model on a few dimensions (in Amazon's data, style and fluency) and worse on the rest.
Does fine-tuning on post-edits improve a new translation model?
Not by imitation. In Amazon's English to Hindi experiment, supervised fine-tuning on 24k post-edits raised BLEU by 8.4 points but the share of segments passing all MQM checks by only 1.8 points. DPO moved it by -0.4. StalePO, which pushes both responses' likelihood down and anchors to the model's own output, raised it by 14.9.
Can I use COMET or BLEU against post-edits to choose between MT engines?
Not reliably. In arXiv:2609.16340 the system with the largest MQM gain scored lowest on COMET, chrF and BLEU against the post-edits, and across eight systems COMET ranked them in nearly the opposite order (Spearman -0.71, our calculation from the paper's tables).
What does StalePO cost in accuracy?
On English to Hindi, accuracy pass rate fell 5.4 points under the LLM judge and 3.5 under professional translators, mostly minor untranslated spans. Mistranslations and omissions were nearly unchanged.
Which model and judge did Amazon use?
GPT-OSS 120B fine-tuned with QLoRA, judged by seven binary MQM scorers built on Claude Sonnet 4.5, with professional translators re-annotating 2,000 English to Hindi segments.