Can Scene Text Recognition Read Rare Compositions?

• URL: http://arxiv.org/abs/2609.00816v1
• Date: Tue, 01 Sep 2026 07:16:42 GMT
• Title: Can Scene Text Recognition Read Rare Compositions?
• Abstract summary: Scene text recognition is reported as 89--97% accurate on the six standard benchmarks, and the problem is widely treated as saturated.<n>We present an alternative reading.<n>When the same test images are stratified jointly by ground-truth word rarity and character n-gram novelty against a reference corpus, accuracy at the rareword x rare-trigram corner of the resulting 5x5 grid drops 10--18 pt below the q3/q3 centre.
• Score: 1.7844382164707184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scene text recognition is reported as 89--97% accurate on the six standard benchmarks, and the problem is widely treated as saturated. We present an alternative reading. When the same test images are stratified jointly by ground-truth word rarity and character n-gram novelty against a reference corpus, accuracy at the rare-word x rare-trigram corner of the resulting 5x5 grid drops 10--18 pt below the q3/q3 centre across nine English specialised recognisers, and the same direction (corner below centre) holds on all 13 of 13 (language, model) pairs we test across four writing systems (Latin, Han, Han+kana, Arabic). The drop is not a capacity bottleneck. A 6x vision-backbone scale-up (CLIP4STR-Base 158M -> CLIP4STR-Huge 1.0B, OpenCLIP ViT-H/14 LAION-2B) leads every benchmark in aggregate accuracy yet leaves the stress corner unchanged (86.9 -> 86.5, within paired-bootstrap noise). Four converging probes--layer-wise probing, confidence-when-wrong, attention re-balancing, and a cross-script commit-vs-abstain error split--localise the failure to the autoregressive decoder's lexical prior. We then ask how much of the gap existing techniques recover. Of 16 non-architectural mitigations, the largest mean q5/q5 gain is +1.3 pt and none clears the paired-bootstrap noise floor; the only intervention that does is the architectural shift from autoregressive to CTC decoding (SVTRv2, +2.5 pt, p=0.02, n=474). A confidence-routed AR-CTC ensemble adds a directionally consistent +0.6 pt that stays within noise, and its dominant learned coefficient is each model's own minimum-softmax confidence--independently echoing the mechanism above. No configuration we test improves both the compositional corner and aggregate accuracy. The rare-input long tail thus points to architectural change rather than added capacity.

Related papers

• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs [0.23438564092609357]
  Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites accumulate.<n>PTQ is now the default deployment path for open-weight models, yet its effect on this failure mode has not been tested.<n>We evaluate three precision levels (FP16, INT8, INT4/NF4, via bitsandbytes) across three architecturally distinct instruction-tuned models.
  arXiv  Detail & Related papers  (2026-08-19T06:17:13Z)
• IndicQE-APE: A Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages [77.88427845181154]
  We consolidate the WMT 2020--2024 shared-task lineage with an extended English--Malayalam resource into indicqe: $126,754$ instances over nine directional pairs.<n>We benchmark six prompted LLMs and three COMET metrics on segment-level QE, and three systems on APE.
  arXiv  Detail & Related papers  (2026-08-17T09:50:52Z)
• Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG [45.88028371034407]
  Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content.<n>We introduce QIMG-7, a benchmark for multimodal retrieval pollution in multi-sentence factual QA.<n>We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers.
  arXiv  Detail & Related papers  (2026-07-12T15:13:09Z)
• Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts [0.0]
  We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved.<n>We classify 30,000 chain-of-thought outputs from five instruction-tuned LLMs across three quantization precisions.<n>We find that while accuracy is robust across precisions, Hollow Convergence shows a significant size-dependent shift under NF4.
  arXiv  Detail & Related papers  (2026-07-10T21:55:05Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks [0.0]
  A paraphrase-quality audit of MathCheck detected 4 semantically incorrect paraphrases in 129 groups.<n>Removing them drops GPT-4o from rank 2 to rank 4 and elevates Claude Haiku and DeepSeek V3 above it.
  arXiv  Detail & Related papers  (2026-05-27T18:59:18Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• The frame-level leakage trap: rethinking evaluation protocols for intrinsic image decomposition, with source-separable uncertainty as a case study [0.0]
  We quantify the leakage effect for the first time, across three architectures.<n>A frame-level split inflates test R_PSNR by 1.6 to 2.0 dB relative to a scene-level split.<n>We present a physics-informed decomposition I = R composed with S + N with a source-separable three-way heteroscedastic uncertainty head.
  arXiv  Detail & Related papers  (2026-05-07T14:37:16Z)
• The Digital Afterlife of Empires: Four Language Models Converge on the Same Imperial Cartography of Writing [0.0]
  Large language models process the world's writing systems with radical inequality.<n>Only 29 scripts (9.7%) are fully supported by contemporary digital infrastructure; among 158 living scripts, 60 (38.0%) lack complete support.<n> Tokenizer efficiency varies by a factor of 31.7 across 45 scripts measured with parallel text.
  arXiv  Detail & Related papers  (2026-04-30T07:02:45Z)
• Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing [55.97957664897004]
  An effective recipe for building seq2seq, non-autoregressive, task-orienteds to map utterances to semantic frames proceeds in three steps. These models are typically bottlenecked by length prediction. In our work, we propose non-autoregressives which shift the decoding task from text generation to span prediction.
  arXiv  Detail & Related papers  (2021-04-15T07:02:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.