Skip to main content

Knowing When to Correct: Cost-Aware LLM Routing for OCR Post-Correction in Historical Documents

[!NOTE] Overleaf Project: git.overleaf.com/6a1d78e803cbdf7def32a839
Last Synced: 2026-09-29 11:35:05 (via PA Git Sync)
Source File: paper/main.tex

Venue: ACM

Knowing InternationalWhen Conferenceto onCorrect: InformationCost-Aware andLLM KnowledgeRouting Managementfor (CIKM)
OCR Post-Correction in Historical Documents

Authors: Stergios Konstantinidis, Hayman Lotfy, Michalis Vlachos
Affiliation:

Department

[!ABSTRACT] Historical digital archives present new challenges for retrieval systems because of InformationOCR Systemserrors introduced by degraded page quality, old typefaces, and complex page layouts. Large language models (DESI),LLMs) HECoffer Lausanne
GitHuban Public:effective CIKM_public
Overleafmeans Project:of https://git.overleaf.com/6a1d78e803cbdf7def32a839
Corecorrecting Codebase:transcription /Users/stergios/Documents/GitHub/Optimizing-errors. However, applying LLM-based-OCR-Corrections

based correction at scale can become prohibitively expensive. We investigate a selective, cost-aware strategy for LLM-assisted OCR post-correction, using a regression-guided router to predict when LLM correction is likely to improve transcription quality, thereby reducing unnecessary LLM processing and associated costs while preserving historically valid text. We evaluate this strategy on a dataset comprising historical Swiss newspapers published between 1733 and 1945. Our results show that selective correction can retain most of the quality gains of full correction while substantially reducing the LLM token cost. Using Tesseract OCR, sending all text segments for LLM correction improves CER from 6.3% to 2.9% (best approach). In contrast, our regression-guided router achieves CER of 3.1% (0.2% worse) while avoiding routing 40% of segments for LLM correction. Finally, we show that our regression-guided LLM router closely trails the decisions of an oracle that knows in advance which segments benefit from correction.

\city{Lausanne} \country{Switzerland}}

\city{Lausanne} \country{Switzerland}}

\city{Lausanne} \country{Switzerland}}

\renewcommand{\shortauthors}{Konstantinidis et al.}

\begin{CCSXML} <concept_id>10010405.10010497.10010504.10010505</concept_id> <concept_desc>Applied computingDocument analysis</concept_desc> <concept_significance>500</concept_significance> <concept_id>10010147.10010178.10010179.10010182</concept_id> <concept_desc>Computing methodologiesNatural language generation</concept_desc> <concept_significance>300</concept_significance> \end{CCSXML}

\keywords{OCR Correction, Large Language Models, Historical Newspapers, Cost-Effectiveness, Document Analysis, Selective Routing}

1. Problem StatementIntroduction

AtHistorical multi-millionnewspapers pageare scale,valuable sources for historians, social scientists, and cultural heritage researchers. However, many digitized archives remain difficult to use because OCR systems often introduce transcription errors on historical material [piryani2025evaluating]. Old typefaces, damaged paper, ink bleed-through, irregular spelling, and complex layouts all contribute to high word-error-rates (WER) [holley2009good,alex2012digitised].

Large language models (LLMs) can correct many OCR errors after transcription using textual context. However, using an LLM for refining every OCR output can be costly at archive scale and may be unnecessary when the OCR text is already accurate. In some cases, correction can even introduce new errors by altering historically valid spelling or typography.

This paper addresses the problem of reducing the cost of LLM-based OCR post-correction while sacrificing as little transcription quality as possible. We study whether information available at OCR time, especially character-level confidence scores, can guide the selection of text segments that should be submitted to an LLM for correction. The proposed approach is evaluated on historical newspaper material from the Canton of Vaud, Switzerland, comprising nine publications issued between 1733 and 1945. Through this evaluation, we make two key contributions:

* First, we formulate cost-aware post-OCR correction as a lightweight binary routing problem and propose a regression-guided router that predicts the expected correction benefit of each segment relative to its token cost.
* Second, on historical newspaper archives across multiple OCR engines and LLMs, we demonstrate that our router closely trails an optimal oracle, capturing more than $96%$ of full-correction CER (character-error-rate) gains while reducing token costs by more than $40%$.

Post-OCR correction is constrainedgradually moving from rule-based and statistical methods toward context-aware deep learning approaches and, more recently, LLMs [nguyen2021survey]. Early approaches relied on the noisy-channel model [kissos_ocr_2016], often using isolated-word correction and feature-based classification. However, these methods frequently struggle with real-word errors (incorrectly recognized words that nevertheless exist in a standard dictionary) which can account for up to 59.0% of all OCR inaccuracies, according to recent studies [10.1007/978-3-031-70442-0_13].

\medskip\noindentConfidence-Aware Detection and Hybrid Models. A growing line of work uses the confidence scores produced internally by cost:

OCR
    engines Fullas a signal for locating likely errors. Most relevant to us, Hemmer et al. [10.1007/978-3-031-70442-0_13] propose ConfBERT, an OCR error-detection model that fuses these scores with contextual language representations. Each token's OCR confidence is injected into its BERT embedding through a learnable mixing parameter, letting the model weigh textual context against the engine's own certainty when predicting whether a token is erroneous. In contrast, we learn a cost-aware, segment-level routing decision. While token-level error detectors (like ConfBERT) identify noise presence, error presence does not guarantee LLM correctionrepairability costsnor hundredsaccount for token cost. We combine OCR confidence with surface statistics, orthographic/lexicon features, and document metadata to directly estimate expected CER reduction per token spent. As the most directly comparable confidence-aware method, we re-implement ConfBERT as a segment-level router on our corpus in our experiments.

    \medskip\noindentLanguage Models. Lately, LLMs are being increasingly used across various stages of thousandsthe OCR and post-OCR pipeline, though not without challenges; recent work has shown that LLMs can improve post-OCR correction for historical newspapers [thomas2024leveraging]. However, evaluations across historical transcription benchmarks show that LLM performance varies substantially with model choice, prompt design, document type, language, and initial transcription quality [boros2024post]. Sohail et al. [sohail2024decipheringunderservedbenchmarkingllm] benchmarked multimodal models like GPT-4o for low-resource scripts, noting that while LLMs offer context-aware alternatives to conventional OCR, their performance remains sensitive to visual distortions and script complexity in zero-shot settings. Comprehensive benchmarks such as CC-OCR [yang2024ccocrcomprehensivechallengingocr] further emphasize the challenges of dollarsusing LLMs for complex literacy tasks. Shi and Chen [10.1117/12.3068186] route OCR outputs when confidence falls below 0.95; however, raw confidence ignores text length and error repairability. Multi-LLM routers (e.g., RouteLLM [Ong2025RouteLLMLT, li2025costaware], PILOT [panda2025pilot], ParetoBandit [tabernermiller2026paretobandit]) dispatch queries between strong and weak LLMs, but still invoke an LLM for every request via dense embeddings. In contrast, our router decides whether each segment should be sent to an LLM for correction at all, using lightweight features that require no GPU-based inference at routing time.

    \medskip\noindentHistorical Archives and Digital Humanities. Historical document digitization presents challenges that standard OCR pipelines often fail to address. Backer and Hyman [backer-hyman-2025-bootstrapping] point out that WER and CER can understate how useful a system is for historical research, and they call for discipline-driven evaluations'' that match the needs of humanities scholars. A related problem is the *modernization trap* [hammarstrom2025investigation], where a cleaning step rewrites old spellings into their modern form. For example, the OCR may correctly read the historical French word *seroit*, but the cleaning step then changes it to the modern *serait* (*seroit* $\rightarrow$ *serait*). This kind of correction'' loses the original spelling and weakens the fidelity of the source.

    Our approach, by combining domain-specific features with selective, cost-aware routing, aims to balance LLM benefits against the cost and fidelity requirements of large-scale historical archives.

    Methodology

    We approach OCR post-correction as a selective routing problem: rather than sending every transcription to an LLM, we decide per segment whether correction is likely to improve transcription quality, using only signals available before any correction is run (see Figure [fig:methodology]). This section formalizes that decision and its quality-cost trade-off. We refer to each unit of text that is routed as a whole as a segment.

    \begin{figure}[ht] \centering \includegraphics[width=\linewidth]{paper/figures/overview.png} \caption{Overview of our learning-driven, cost-aware correction methodology.} \label{fig:methodology} \vspace{-1.5em} \end{figure}

    \medskip\noindentSetup: correction utility. Let $\mathcal{D} = {d_1, \dots, d_n}$ be a corpus of text segments. Each segment $d_i$ has a raw OCR transcription $d_i^{\text{raw}}$. During evaluation, we also obtain an LLM-corrected version $d_i^{\text{corr}}$, which allows us to measure how much the correction improves transcription quality. We score quality using the Character Error Rate $W(\cdot)$ against the ground truth. The routing problem is therefore to identify, before running the LLM, which segments are likely to benefit from correction. We formalize this decision through two quantities measured per segment after evaluation: the realized correction gain and the number of tokens that would need to be processed.

    * the **benefit** of correction, i.e.\ the reduction in error it
    yields,
    \begin{equation}
        \Delta_i \;=\; W\!\left(d_i^{\text{raw}}\right) - W\!\left(d_i^{\text{corr}}\right);
    \end{equation}
    * the **cost** of correction, $C(d_i) = |d_i|$, the segment length
    in tokens, which is what LLM pricing scales with.
    

    A positive $\Delta_i$ means correction helps; a negative value means it hurts; for instance by normalizing historically valid spelling. The difficulty is that $\Delta_i$ depends on national$d_i^{\text{corr}}$ archivaland collections.

    so Manyis archivalunknown passagesat the moment we must decide whether to correct.

    \medskip\noindentPredicting correction utility. We therefore estimate the benefit from the raw text alone. A feature map [ \phi: \mathcal{D} \to \Phi \subseteq \mathbb{R}^{54} ] encodes each segment as a feature vector $\phi(d_i)$ in the feature space $\Phi$; these are alreadythe accurate;54 invokingfeatures LLMscomprising surface statistics, orthographic/lexicon features, OCR confidence, and document metadata derived from the text segment. A model $\mathcal{M}_\theta$ with learnable parameters $\theta$ maps features to a predicted correction utility $\hat{u}i = \mathcal{M}\theta(\phi(d_i))$ which can be instantiated in either of two forms:

    * **Regression**, $\mathcal{M}_\theta: \Phi \to \mathbb{R}$,
    predicting the expected error reduction directly,
    $\hat{u}_i = \hat{\Delta}_i \approx \mathbb{E}[\Delta_i]$;
    * **Classification**, $\mathcal{M}_\theta: \Phi \to [0,1]$,
    predicting the probability that correction is net-positive,
    $\hat{u}_i = P\!\left(\Delta_i > 0 \mid \phi(d_i)\right)$.
    

    In both cases $\theta$ is fitted on themsegments introduceswith latency,known cost,$\Delta_i$, and riska larger $\hat{u}_i$ marks a stronger candidate for correction. Our implementation and experiments adopt the regression approach, using Lasso with cross-validated regularization selection (LassoCV) as the estimator. Comparative results for alternative regression models are available in our repository\footnote{https://github.com/Stergios-Konstantinidis/CIKM_public}.

    \medskip\noindentCost-aware priority score. Ranking by predicted benefit alone would over-spend on long segments. We instead rank by benefit per unit cost: \begin{equation} \hat{s}i ;=; \frac{\mathcal{M}\theta(\phi(d_i))}{C(d_i)} ;=; \frac{\hat{u}_i}{|d_i|}. \end{equation} The intuition is that under a fixed token budget the relevant question is not will this segment improve?'' but how much improvement do we get per token spent?'' For the regression model, $\hat{s}_i$ reads directly as expected CER reduction per token; for the classification model it acts as a cost-discounted likelihood of hallucinations.

    benefit. Either way, prioritizing high-$\hat{s}_i$ segments favors corrections that are both likely to help and are inexpensive (most quality under a given budget).

    \medskip\noindentCoreRouting Researchpolicy Questions:and frontier. Sorting segments by priority score yields a permutation $\pi$ of ${1,\dots,n}$ with \begin{equation} \hat{s}{\pi(1)} \geq \dots \geq \hat{s}{\pi(n)}. \end{equation} For a budget of $k$ corrections we route the segments in [ R = {\pi(1),\dots,\pi(k)} ] to the LLM and keep the rest as raw OCR. Equivalently, we correct every segment whose score exceeds a cutoff. Routing replaces the raw text of each segment in $R$ with its correction, so the residual CER (the unweighted mean of per-segment errors) is \begin{equation} \begin{aligned} \widetilde{W}(k) &= \frac{1}{n}!\left( \sum_{i \notin R} W!\big(d_i^{\text{raw}}\big) + \sum_{i \in R} W!\big(d_i^{\text{corr}}\big) \right) \[2pt] &= \frac{1}{n}!\left( \sum_{i=1}^{n} W!\big(d_i^{\text{raw}}\big) - \sum_{i \in R} \Delta_i \right) ;=; W_0 - \frac{G(k)}{n}, \end{aligned} \end{equation} where $W_0 = \tfrac{1}{n}\sum_{i} W!\big(d_i^{\text{raw}}\big)$ is the uncorrected baseline CER and $G(k) = \sum_{i \in R}\Delta_i$ is the cumulative gain. Note that this algebraic derivation is metric-agnostic: it holds for any evaluation metric $W(\cdot)$ that is macro-averaged over the corpus segments. Because $W_0$ and $n$ are constants, the residual error rate is a strictly decreasing affine function of the gain, so maximizing $G(k)$ is exactly equivalent to minimizing $\widetilde{W}(k)$. Sweeping $k$ from $0$ to $n$ traces a continuous routing frontier of residual CER against token budget (Figure [fig:routing_frontier]), along which any operating point can be selected.

      \begin{figure*}[t!]

      \centering \includegraphics[width=\textwidth]{results/figures/routing_frontier/lassocv/routing_frontier_0pp.png} \caption{Routing frontier comparing four OCR-correction strategies: LLM Oracle, Spell-check baseline, ConfBERT [10.1007/978-3-031-70442-0_13], and our regression-guided router. AUC is annotated per curve. The secondary x-axis (top) reports cumulative tokens submitted to the LLM (Gemini~3 Flash).} \label{fig:routing_frontier} \end{figure*}

      Experimental Results

      \label{sec:experiments}

      We structure the evaluation around three research questions:

      * **RQ1:** How closely does our selective routing match the theoretical oracle ceiling,oracle,
      and does it outperformimprove naiveon confidenceconfidence-based thresholding?
      routing? * **RQ2:** How well does the regression-estimated improvement $\hat{Δ}_i\Delta}_i$ correlate with the true realizedactual improvement Δi?$\Delta_i$ measured after LLM correction? * **RQ3:** What is the actual operationalLLM cost saved when routingonly onlythe segments predicted to benefit are corrected, and how does it vary across variousmodels?

      \medskip\noindentCorpus and annotation. We use the corpus summarized in Table [tab:corpus]: 609 text segments from nine Swiss historical newspapers (1733--1945) in the Canton of Vaud archives. Three French speakers produced fidelity-oriented transcriptions preserving historical spelling and source anomalies. We report WER/CER after typographic normalization unifying character variants and spacing. Fitting the Lasso router on 54 features takes $<0.1$,s on a single CPU core.

      \begin{table}[h] \centering \caption{Corpus composition by newspaper publication.} \vspace{-\baselineskip} \label{tab:corpus} \resizebox{0.78\columnwidth}{!}{ \begin{tabular}{@{}lcccc@{}} \toprule Newspaper & Dates & Issues & Pages & Text \ & & & & segments \ \midrule La Revue & 1875--1945 & 4 & 5 & 139 \ Feuille d'Avis & 1762--1841 & 4 & 13 & 131 \ Tribune de Lausanne & 1912 & 3 & 4 & 105 \ Nouvelliste Vaudois & 1822--1840 & 3 & 7 & 90 \ Petite Revue & 1943 & 1 & 1 & 46 \ Lausanne Artistique & 1926 & 1 & 1 & 32 \ Almanach & 1832 & 1 & 8 & 31 \ Estafette & 1862 & 1 & 1 & 19 \ Mercure Suisse & 1733--1738 & 2 & 5 & 16 \ \midrule Total & 1733--1945 & 20 & 45 & 609 \ \bottomrule \end{tabular} } \end{table}

      \medskip \noindentOCR engines and LLMs. We run three OCR engines (PaddleOCR v3 [cui2025paddleocr], EasyOCR\footnote{https://github.com/JaidedAI/EasyOCR}, Tesseractv5 [tesseractOCR]) and six correction LLMs spanning closed-source (Gemini3 Flash, Gemini3.1 Flash Lite, GPT-4o) [google2025gemini3flash,openai2024gpt4osystemcard] and open-weight (Qwen2.5-72B, Llama3.3-70B, Gemma4-31B) [qwen2024qwen25,meta2024llama33,google2026gemma4] models, each with its best prompt out of ten templates of increasing complexity. Because of space restrictions, the paper reports results using Tesseract OCR and Gemini~3 Flash; evaluations across additional engines, LLMs, and prompt ablations are available in our repository.

      \medskip\noindentBaselines and protocol. We compare our regression-guided router (ranking segments by predicted improvement per token $\hat{s}_i = \hat{\Delta}_i / |d_i|$) against: (1) Full LLM correction (correct all segments), (2) ConfBERT [10.1007/978-3-031-70442-0_13] (BERT with token-level confidence injection), (3) spell-checking (pyspellchecker), (4) random routing, and (5) an Oracle routing by true error reduction $\Delta_i$. The regression uses 54 features computed from raw OCR alone (37 surface statistics, 4 orthographic/lexicon features, 1 OCR confidence score, and 12 document metadata features; full list in the repository), evaluated with leave-one-out cross-validation (inner 10-fold CV for regularization). We summarize each strategy by the area under its frontier LLMs?

      (AUC) of
      residual

      ProblemCER Visualand Illustration

      WER
      against
      routing
      budget; lower is better.

      \smallskip\noindent RQ1: Routing Quality vs.\ Oracle. Figure 1:[fig:routing_frontier] Typicalshows the WER/CER routing frontiers. Across the entire budget, our router closely tracks the theoretical upper bound of the Oracle, achieving the lowest residual error curves and substantially outperforming ConfBERT, raw OCR degradationconfidence thresholding, and random routing.

      Table [tab:routing_comparison] compares operating points across budget tiers. Full LLM correction establishes the quality ceiling but incurs maximum token spend. In contrast, dictionary spell-checking proves to be the worst intervention for character accuracy: while it marginally improves WER on common modern terms, it actively degrades CER by corrupting valid historical spellings. Random routing improves error rates only linearly with budget without prioritizing high-yield segments. ConfBERT improves upon random selection, but remains consistently inferior to our method. Across all operating points, our regression-guided router delivers the best performance, recovering nearly all achievable quality gains while substantially cutting token expenditures.

      \smallskip\noindentAdditional OCR Engines. These results generalize across OCR engines: on both high-accuracy engines (PaddleOCR) and noisier baselines (EasyOCR), our router captures the vast majority of full LLM correction gains while routing only a subset of segments (results in the repository).

      \begin{table}[h] \centering \caption{Routing comparison on Tesseract OCR, using Gemini~3 Flash for LLM correction. CER and WER report the corpus-level error rate after applying each method.} \label{tab:routing_comparison} \resizebox{\columnwidth}{!}{ \begin{tabular}{@{}l|cccc|c@{}} \toprule Method & CER & WER & Segs. & Token & CER \ & & & Corrected & Savings & Improv. \ \midrule Baseline OCR (no correction) & 0.063 & 0.234 & 0% & 100% & 0% \ Spell-check & 0.068 & 0.228 & 100% & N/A & $-$6.80% \ \hline Random routing (40% segments) & 0.050 & 0.179 & 40% & 60.0% & +21.2% \ ConfBERT (Top 40% segments) & 0.042 & 0.159 & 40% & 39.6% & +33.2% \ Our approach (Top 40% segments) & 0.033 & 0.120 & 40% & 65.2% & +48.4% \ \hline Random routing (60% segments) & 0.043 & 0.152 & 60% & 40.0% & +31.7% \ ConfBERT (Top 60% segments) & 0.037 & 0.133 & 60% & 15.6% & +41.9% \ Our approach (Top 60% segments) & 0.031 & 0.107 & 60% & 41.0% & +51.2% \ \hline Random routing (80% segments) & 0.036 & 0.124 & 80% & 20.0% & +42.3% \ ConfBERT (Top 80% segments) & 0.032 & 0.118 & 80% & 2.5% & +49.7% \ Our approach (Top 80% segments) & 0.030 & 0.100 & 80% & 11.8% & +52.1% \ \hline Full LLM (all segments) & 0.029 & 0.097 & 100% & 0% & +52.9% \ \bottomrule \end{tabular} } \end{table}

      \smallskip\noindent RQ2: Predicting CER Improvement. RQ1 depends on ranking segments by predicted improvement, so we next ask how well $\Delta_i$ can be recovered from raw OCR text alone, without access to ground truth. Figure [fig:wer_prediction] plots predicted against actual $\Delta_i$ on held-out segments (leave-one-out with 10-fold inner CV for regularization); the regression attains a Spearman rank correlation $\rho = 0.580$ ($p < 10^{-53}$). The correlation is moderate, but the router needs to rank segments by expected benefit, not to predict $\Delta_i$ exactly. The RQ1 frontier confirms that this ranking is strong enough to beat the ConfBERT baseline and closely approach the oracle.

      \begin{figure}[t!] \centering \includegraphics[width=0.7\linewidth]{paper/figures/predicted_vs_actual_cer_loo_cv10.pdf} \vspace{-\baselineskip} \caption{Predicted vs actual CER improvement $\Delta_i$ on held-out segments (leave-one-out).} \label{fig:wer_prediction} \vspace{-1.5em} \end{figure}

      \smallskip\noindent RQ3: LLM Cost. In budget-constrained deployments (Table [tab:routing_comparison]), routing is done as follows: segments are ranked by priority score $\hat{s}_i$ and the top-$k$ are selected to match the available token budget. In unconstrained settings without an explicit budget, cross-validation yields an optimal cutoff of $\hat{\Delta}_i > 0.03$ to guard against marginal regressions. Table [tab:llm_cost] compares full-correction costs against this unconstrained routing strategy across several LLMs. The Gemini Flash family provides the best quality/cost balance among the commercial models. Older premium models such as GPT-4o incur higher cost without appreciable quality gains; open-source models occupy an intermediate band at zero API cost.

      \smallskip\noindentTraining Cost and Amortization. The router setup requires minimal overhead on the seed corpus ($N=609$): $\sim$40 annotator-hours ($\sim$4,min/segment) and $<1$,s CPU fitting. Even spanning extensive evaluations across multiple OCR engines, prompt variations, and LLMs, our total exploratory API expenditure was $$16$ ($\approx$0.50$ for a single production setup), which is rapidly amortized by $>40%$ token savings at scale.

      \begin{table}[h!] \centering \caption{LLM inference cost comparison on Tesseract OCR. Full correction (Cost (full)'') vs.\ our routing (Cost (routed)''). Open-source models have $$0$ API cost.} \label{tab:llm_cost} \resizebox{\columnwidth}{!}{ \begin{tabular}{@{}l|rr|cc|rr@{}} \toprule LLM Model & \makecell{CER\(full)} & \makecell{WER\(full)} & \makecell{CER\(routed)} & \makecell{WER\(routed)} & \makecell{Cost\(full)} & \makecell{Cost\(routed)} \ \midrule Gemini 3 Flash & 0.029 & 0.097 & 0.033 & 0.120 & $0.182 & $0.064 \ Gemini 3.1 Flash Lite & 0.040 & 0.109 & 0.048 & 0.154 & $0.087 & $0.031 \ GPT-4o & 0.049 & 0.128 & 0.046 & 0.154 & $0.738 & $0.259 \ Gemma 4-31B & 0.039 & 0.123 & 0.043 & 0.150 & $0 & $0 \ Qwen 2.5-72B & 0.058 & 0.208 & 0.060 & 0.169 & $0 & $0 \ Llama 3.3-70B & 0.137 & 0.230 & 0.072 & 0.180 & $0 & $0 \ \midrule No correction& 0.063 & 0.234 & 0.063 & 0.234 & --- & --- \ \bottomrule \end{tabular} } \end{table}

      \vspace{-0.1em}

      Conclusion

      The indiscriminate use of LLMs can render large pipelines expensive. We presented a lightweight, cost-aware router for OCR post-correction in historical periodicalsarchives. requiringThe cost-awarefeature-based routing.regression model predicts when correction is beneficial: correcting 60% of segments brings CER within 0.2% of full correction and closely trails an oracle. This routing principle, of predicting the LLM utility before paying for inference, extends naturally to other cascade tasks such as post-correction of speech or translation.

      \smallskip\noindentLimitations and Failure Modes. Our evaluation focuses on historical Swiss French newspapers (1733--1945). While surface and confidence features are language-agnostic, orthographic features require a target lexicon. Error analysis reveals two primary failure modes: (1)Hallucinatory Modernization, where archaic syntax or valid 18th-century spellings are routed and standardized to modern French by the LLM as shown in Figure [fig:sample_modernization]; and (2)Irrecoverable Degradation, where severe physical damage yields illegible text that neither OCR nor LLM can reconstruct (such as in Figure [fig:sample_degraded]), thus consuming tokens with little corresponding improvement.

      \begin{figure}[t!] \centering \fbox{\includegraphics[width=\linewidth]{paper/figures/issue_7_page_2_region_4277.png}} \vspace{-\baselineskip} \caption{Sample segment: areas highlighted in blue indicate segments prone to the modernization trap, while areas highlighted in red indicate instances where an OCR machine would misinterpret the letter S as F.} \label{fig:sample_modernization}

      \end{figure}

      \begin{figure}[t!] \centering \fbox{\includegraphics[width=0.99\linewidth]{paper/figures/issue_292_wide_plain.jpg}} \vspace{-.6\baselineskip} \caption{Scanned newspaper with irrecoverable degradation} \label{fig:sample_degraded} \end{figure}

      Acknowledgments

      Supported by Swiss National Science Foundation, Grant No. 237991.

      GenAI Usage Disclosure

      GenAI was used as a code assistant and for formatting and editing the final manuscript. Research ideas are the authors' own. The authors take full responsibility for this work.

      \bibliographystyle{ACM-Reference-Format} \bibliography{main}