paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Tianyi Guan, Yiding Wang, Haotong Yang, Siyuan Cao, Shirui Liu, Yi Hu, Jiaqi Li, Muhan Zhang

Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge this gap, we introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning. It covers five representative domains, each containing 100 interconnected subtasks ordered by increasing difficulty and opportunities for cross-task skill reuse. Our experiments show that sequential execution generally improves performance, but the gains vary substantially across models and domains. Moreover, in-context learning performs comparably to explicit skill maintenance on average, suggesting that much of the improvement arises from adaptation to prior context and feedback rather than reusable skill abstraction alone. Explicit skills nevertheless provide selective benefits for tasks requiring reusable procedures or precise outputs. We further find that less capable models tend to accumulate larger, more fragmented collections of task-specific skills. These findings show that current in-context skill evolution mechanisms can support continual adaptation, but still struggle to consistently consolidate experience into robust and transferable skills.

arXiv

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad

We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K. In contrast, an MS MARCO-trained cross-encoder reranker reduces precision on the scientific corpus, suggesting that domain mismatch can outweigh the benefits of stronger query-passage interaction. Generation faithfulness measured with RAGAS increases with corpus scale in our setup. Retrieval evaluation uses pseudo-relevance labels derived from the hybrid system, so we treat the results as controlled comparative evidence rather than a benchmark claim. We release code, indexes, and evaluation outputs to support replication and follow-up studies.

arXiv

Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling

Nathan Labiosa, David Buff, Ena Nayak, Erica Donno

When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate. Across a five-model panel we identify two propagation regimes - spike-and-suppress (Phi-3.5, Gemma-2-9B) and late-accumulation (Llama-3, Mistral, Qwen2.5-7B) - and on the two models meeting an 80% identity-patch gate, sensitivity and causality are anti-correlated (rho = -0.72 to -0.88). Within-family scaling on Qwen2.5 (1.5B to 14B) shows the late-accumulation signature strengthening monotonically with scale, corroborated on a second family. We propose cascade disruption as the mechanism behind the dissociation: adapters placed at causally implicated early layers break intact downstream computation, making diagnostic-flagged sites the worst adapter placements. A fixed-harness layer sweep across four models (3.8-8B) confirms the core prediction on chain-of-thought GSM8K - the flagged sites are the most damaging adapter windows on every adjudicable model - and is sign-consistent but strongly attenuated on a multiple-choice control, consistent with damage that compounds with generation length. The sweep yields practical guidance: a training-free LRD pre-screen and a default-deepest placement rule, though absolute gains over no-adapter baselines remain small. Finally, apparent gains from a representation-stability loss reverse under an adequate generation budget - truncated chain-of-thought had been scored as empty - a methodological warning for any intervention evaluated on chain-of-thought tasks.

arXiv

VIBE: A VAD-Informed Benchmark for Entity-Centered Affective Profiling of Large Language Model Outputs

Andrei Chetvergov, Alexander Evseev, Timofei Sivoraksha, Stepan Ukolov, Mikhail Solovev, Danil Sazanakov, Sergey Bolovtsov

Large language models routinely describe socially salient targets, including political figures, countries, religions, organizations, historical events, and social groups, encoding affective framing alongside factual content: a target may appear favorable or threatening, calm or conflictual, powerful or vulnerable. Existing work captures parts of this space through sentiment, favorability, and emotion benchmarks, but none combines target-directed VAD attribution, an explicit scorer contract, and a passport reporting format. We introduce VIBE, a benchmark for entity-centered affective profiling of LLM outputs in Valence-Arousal-Dominance (VAD) space. Its core contribution is a measurement contract: VIBE separates generation from external scoring, distinguishes scalar favorability, response-level VAD, and target-directed VAD, and reports profiles through an Affective Passport. Three empirical layers support the contract. H1 shows scalar favorability does not subsume arousal and dominance: valence findings are cross-validated (rV = 0.944 judge-human, rV = 0.954 inter-scorer); arousal and dominance are single-scorer directional estimates, not point-precise, consistent with known inter-annotator difficulty on these axes (rA = 0.495, rD = 0.702 among human annotators). H2 shows whole-response and target-directed VAD are different contracts: the same text can carry one affective tone overall while representing the named target differently. H3 is a protocol-drift diagnostic: elicitation conditions shift profiles, motivating context metadata in every affective report. These results motivate entity-centered affective profiling as a documented practice: profiles should be released with scorer identity, coverage, protocol, and interpretation limits.

arXiv

M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models

Tomáš Burkert, Angelika Peljak-Łapińska, David Zelený

Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a language rather than whether it commands the language itself, conflating fluency with proficiency. We introduce M-GATE (Multilingual Grammar, Accuracy in Translation, and Efficiency), a benchmark of linguistic proficiency spanning 30 typologically diverse languages from high- to low-resource. M-GATE comprises three tasks: grammatical error detection on linguist-crafted, adversarially selected sentences that turn on hard, language-specific phenomena; round-trip translation of shared English sources across 29 target languages, scored by a three-provider LLM judge panel validated against professional annotators; and a supplementary tokenizer-efficiency measure. We evaluate over 50 models in more than 80 configurations. Fluency and proficiency come apart sharply: models that translate competently sit near chance on the adversarial grammar items, the best reaching a Matthews correlation coefficient (MCC) of only 0.36, and their errors lean systematically toward under-flagging, accepting ungrammatical text rather than raising false alarms. Translation quality closely tracks a language's share of pretraining data (r = 0.86 against log Common Crawl share), producing a steep low-resource penalty that is nonetheless narrowing with successive model releases. Enabling reasoning reliably improves translation, while its effect on error detection is smaller and for some models negative, so the best configuration is task-dependent. To resist contamination, test items are kept private behind a continuously updated public leaderboard, with illustrative examples released (https://m-gate.ai).

arXiv

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Bakbergen Ryskulov, Iker García-Ferrero, David Montero, David Jansen, Ali Hashemi, Jezabel R Garcia, Antonio Tiene, Román Orús

Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained from scratch: a compressed model is usually recovered through knowledge distillation (KD). This recovery step largely decides the final quality, yet it is expensive. We present a practitioner's study of how to make distillation training efficient, organised around two systems contributions. First, we show that offline KD (caching the teacher's top-$K$ logits once and training the student against the cache) matches online distillation at near-identical training loss while removing the teacher from memory, running about 29\% faster per iteration, and reaching up to 41\% higher throughput on a single H200 GPU. Second, we introduce a \emph{fused, chunked KL loss} that never materialises the full vocabulary-sized logit tensor, making peak memory linear in the sequence length. This removes the memory spike that otherwise caps context length and lets us train at four times the context (32{,}768 tokens) on a single GPU. A separate output-head-only toy benchmark isolates the loss kernel and confirms its memory and iteration-rate scaling from 4K to 256K tokens. Together these make large-scale healing and hundreds of ablations affordable. We also report supporting ablations on loss design and sequence packing. We release our chunked-loss implementation: https://github.com/CompactifAI/Full-Chunked-KL-Loss.

arXiv

Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks

Shunfan Zheng, Dongsheng Shi, Yue Li, Xin Yi, Linlin Wang, Gerard De Melo

Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current evaluation benchmarks remain disproportionately fixated on Text-to-SQL tasks, neglecting the holistic Database Lifecycle-from initial schema design to post-deployment maintenance. This narrow focus fails to capture the diverse capabilities required for real-world database management. To bridge this gap, we introduce DBLifeBench, the first benchmark to evaluate LLMs across five critical lifecycle phases: Design, Implementation, Operation, Debugging, and Maintenance. Furthermore, addressing the cognitive mismatch between ambiguous natural language and complex SQL logic, we propose Progressive-Text2SQL, a novel task utilizing structured reasoning graphs to mimic human iterative problem-solving. Our extensive evaluation reveals a critical insight: while general-purpose models demonstrate balanced performance, specialized Text-to-SQL models suffer from ``catastrophic forgetting'' in non-coding phases like design and maintenance. DBLifeBench serves as a foundational step toward evaluating and building true full-stack database intelligence.

arXiv

MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models

Tong Ling, Hang Lei, Feng Xiao, Changhui Sun, Jiahang Xie, Hao Liu, Lu Liu, Yanlong Du

Masked diffusion language models (MDLMs) enable parallel generation and bidirectional context modeling, but their positional context differs fundamentally from that of autoregressive (AR) models. Whereas AR decoding exposes a contiguous prefix, MDLM denoising produces dynamic, non-contiguous configurations of revealed and masked tokens. Conventional positional encodings such as RoPE capture sequence order and pairwise displacement but remain insensitive to this evolving token-availability structure. To address this limitation, we propose MDLMPE, a positional encoding designed specifically for masked diffusion. To the best of our knowledge, MDLMPE is the first method to make positional representations explicitly aware of the changing revealed/masked configuration. It represents token availability as a binary sequence, applies distance-aware Gaussian weighting, and projects the resulting pattern through a cosine basis to obtain distribution-aware positional features. These features are added to token embeddings and mapped by a lightweight MLP to angular offsets that modulate the standard RoPE phases. Extensive experiments on LLaDA and DREAM demonstrate that MDLMPE generally outperforms conventional positional encoding methods across supervised fine-tuning, pretraining, zero-shot evaluation, and block-diffusion settings. Further ablations show that the complete combination of availability state, Gaussian locality, spectral basis, and embedding injection yields the strongest result. These results establish the evolving token-availability distribution as a useful positional signal for masked diffusion language models.

arXiv

Risky Business: Measuring The Faithfulness-Safety Tension

Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser, Terry Ruas, Jan Philip Wahle, Bela Gipp

Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring. However, monitoring relies on faithfulness, i.e., the model output strictly derives from its reasoning trace. We identify an alignment tension where a model must be faithful enough to be monitored, yet robust enough to reject unsafe reasoning. We demonstrate that this counterbalance exists in current Large Reasoning Models (LRMs), and show ways in which it can be addressed. We introduce HazMart, a human-written dataset set in an autonomous AI shopkeeper scenario. Unlike prior work that relies on providing hints in prompts to test faithfulness (e.g., "A Stanford professor said it should be Answer A"), we propose a novel replacement-based technique, which we call Targeted Reasoning Replacement (TRR), that directly intervenes in the reasoning chain to substitute in unsafe or illogical thoughts (e.g., "Wait, the answer must be Option B [was Option A] because it is the most fitting"). DeepSeek-R1-Llama-70B exhibits high faithfulness (97.5%) but fails to reject Unsafe Reasoning (12.3%), while QwQ-32B is more robust (73.9% safety) at the cost of lower faithfulness (74.7%). Mechanistic analyses of QwQ-32B reveal that these properties are represented by anti-correlated internal directions peaking at the action-commit token. Finally, we demonstrate that representation steering can independently amplify the safety direction, increasing safe behavior by 9 percentage points while maintaining base capabilities.

arXiv

An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures

Vikas Pahuja, Jonathan Brokman, Omer Hofman, Tamir Nizri, Daniel Vishna, Seraphina Goldfarb-Tarrant, Kelly Marchisio, Hisashi Kojima, Roman Vainshtein

Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is lost when user requests are converted into executable plans. We study the planner in a multi-agent system as the request-to-action interface and derive an actionable taxonomy of planning-grounding failures from failed real-world task executions. LLM-based analysis shows that these failures constitute an increasing share of unsuccessful executions as language-resource availability declines, with the strongest effects in low-resource languages. To test whether the taxonomy supports mitigation, we introduce TART, Taxonomy-Guided Actionable Representation, that makes the taxonomy's key aspects explicit to the planner and downstream sub-agents. Across multiple languages, three LLM backbones, two datasets, and two agentic configurations, TART consistently improves performance. On multilingual GAIA, it raises a state-of-the-art system's accuracy by 5.6 percentage points averaged across eleven languages spanning low- to high-resource settings.

arXiv

Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering

Khaled Ziani

Large language models can generate fluent responses to Islamic questions while introducing factual errors that are difficult to identify. This paper presents our system for \textsc{HalluScoring 2026} Task 2.1, \textit{Islamic Hallucination Detection and Find the Truth}. The task requires a unified two-step prediction: determining whether an Arabic answer generated by an LLM is hallucinated and selecting the verified answer from six closely related candidate options. We use the Islamic knowledge dataset provided by the shared task, which contains 600 question--answer instances, including 341 hallucinated and 259 non-hallucinated answers. Our system is based on the fine-tuned \texttt{google/gemma-4-12B-it} model and uses deterministic decoding during inference. The generated outputs are normalized to extract the hallucination label and the selected option. The system achieves a Macro-F1 score of 0.928 and a label accuracy of 0.935 for hallucination detection, together with an option accuracy of 0.895 for answer selection. These results yield a combined score of 0.912, demonstrating strong performance across both stages of the task. The lower option-selection accuracy indicates that distinguishing the verified answer from plausible alternatives remains more challenging than detecting hallucinated responses.

arXiv

Attention is Case-Sensitive

Maximilian Dillitzer, Tin Stribor Sohn, Jason J. Corso, Michael Auerbach

In human visual perception, uppercase lettering serves as a natural salience cue that captures attention within lowercase text. In this paper, we present a systematic empirical characterization study revealing that Large Language Models (LLMs) exhibit an analogous property: letter casing modulates internal attention allocation. Through analysis across 13 models, nine LLMs and four Vision-Language Models (VLMs), with diverse tokenization schemes, we show that formatting target information in alternating or uppercase against a lowercase context concentrates attention on those textual spans. In text this effect is universal, holding across every evaluated non-reasoning model. We frame it as a previously under-explored latent property of pretrained transformers rather than a prescriptive method. Our investigation reveals a central attention-performance divergence: while this "casing effect" robustly shifts attention, its impact on downstream accuracy is non-trivial, increased concentration does not inherently improve task accuracy and, in high-entropy contexts like alternating case, can degrade it. We further identify a boundary condition: the deliberative "thinking" phase in reasoning models acts as a semantic buffer that mitigates typographic sensitivity in text. Extending the study to VLMs, we find the effect transfers partially: the same prompt-side casing reorganizes cross-modal attention along two coupled axes, predominantly a macroscopic disengagement from the image toward the text prompt, and secondarily a concentration of the residual visual attention on the target region. By isolating casing as a zero-shot mechanism for attention steering that requires no model access or fine-tuning, we provide a new foundational understanding of how pretraining internalizes typographic emphasis.

arXiv

Predicting Deep Neural Network Training Outcomes from Early Training Telemetry

Ranjita Naik, Anh D. Nguyen, Pankaj Kumar Singh

Large hyperparameter sweeps for deep neural networks spend substantial compute on configurations that are effectively doomed from the first few epochs. We study whether a single training run's own early telemetry - per-epoch loss, training accuracy, gradient signal-to-noise ratio, weight-norm growth, and an activation-saturation snapshot - together with its sampled hyperparameters, can predict that run's eventual outcome without reference to other runs. We evaluate three prediction tasks: final test accuracy, relative performance within a domain, and training-dynamics failure, including numerical divergence. Across 23,788 training runs spanning six architecture/dataset combinations, gradient-boosted trees using only the first five epochs of telemetry achieve R^2 = 0.92-0.99 for final-accuracy regression and ROC-AUC = 0.983-0.998 for relative classification on a permanently held-out set of hyperparameter configurations. Useful prediction is already available after a single epoch. A paired ablation shows that gradient- and weight-level telemetry provides a statistically consistent improvement over loss and accuracy curves alone, although the practical gain varies by domain. Transfer is strong between similar architectures, while cross-dataset transfer is limited mainly by differences in accuracy scale rather than loss of the underlying relationship. These results suggest that early-training telemetry can provide a practical decision-support signal for compute allocation while motivating human oversight for any automated intervention.

arXiv

When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills

Yongli Xiang, Zhifang Zhang, Bojun Yang, Ziming Hong, Lei Feng, Miao Xu, Tongliang Liu

Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges defenses designed for individual records or retrieval-based memory. To systematically investigate the safety of the persona-skill pipeline, we introduce AntiSkillBench, an end-to-end benchmark for evaluating risks and defenses across the persona-skill pipeline. It comprises: (i) a dataset of 7,500 persona-grounded dialogue traces, constructed from 50 behaviorally rich profiles spanning diverse task scenarios; (ii) an evaluation suite that measures skill-level privacy leakage and agent-level attribute disclosure and behavioral impersonation across three skill-distillation strategies; and (iii) a defense evaluation covering four configurations across online and post-hoc interventions, including active risk suppression and passive provenance protection. Experiments across three frontier agents show that persona-skill risks persist across agent backbones and distillation protocols, extending from explicit attributes to communication styles and personality traits. Existing defenses exhibit limited and distillation-dependent effectiveness, failing to generalize across risk and distillation strategies. These results highlight AntiSkillBench as a challenging benchmark for developing privacy-preserving and authenticity-aware persona skills.

arXiv

VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations

Ivan Kartáč, Jan Tovarys, Mateusz Lango, Ondřej Dušek

Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in high-stakes domains such as human and veterinary medicine. However, this does not guarantee that generated claims are faithful to the provided excerpts. We present VetScore, a multi-step evaluation method for veterinary long-form question answering, designed to assess how well are generated claims supported by the provided excerpts, weighing this information by each claim's harm potential. VetScore first segments the output and decomposes it into individual claims, then scores each claim with respect to its harm potential and evaluates its faithfulness to source excerpts, and finally calculates the overall risk-adjusted score. We collect an expert-annotated meta-evaluation dataset, evaluate our approach with a range of judge models, and show that it achieves high correlations with veterinary experts even with small judge models, while offering explainability across multiple dimensions.

arXiv

How Closely Do LLM Reviews Align with Human Peer Review?

Abraham Camelo-Guerrero, Jairo Diaz-Rodriguez

Large language models (LLMs) are increasingly used to generate scientific reviews, yet existing evaluations rarely examine whether different providers align with both conference decisions and human reviewing priorities within the same controlled setting. We compare reviews from OpenAI GPT-5.4, Google Gemini 3.1 Pro Preview, and Anthropic Claude Opus 4.6 with human reviews and final decisions for 300 topic-matched ICLR 2026 submissions, equally divided among oral, poster, and rejected papers. Each model reviewed every paper using identical instructions and rating scales after decision information was removed. Our study contributes a cross-provider analysis of three complementary dimensions: alignment with broad and fine-grained decision categories, differences in recommendation-scale usage, and thematic agreement in identified weaknesses. All three LLMs distinguished accepted from rejected papers, but none reproduced the oral versus poster distinction present in human ratings. Scoring patterns were provider-specific: Gemini assigned systematically higher ratings, while OpenAI and Claude were closer to humans for rejected and poster papers but more critical of oral papers. Human and LLM reviews also differed in emphasis, with LLMs more frequently identifying missing baseline comparisons and humans more often raising computational-efficiency concerns. These results show that broad decision alignment does not imply agreement with finer human judgments or reviewing priorities.

arXiv

Decoupling Generation and Selection for Budget-Constrained Faithful Summarization

Zeyu Wang, Guanghua Wang, Meng XU

Abstractive summarization models remain vulnerable to factual inconsistency, redundancy, and weak length control. We propose a modular generation-and-selection framework for sentence-budget-constrained summarization. A pretrained generator produces multiple candidate summaries, which are decomposed into sentence-level candidates. A combinatorial selector then constructs the final summary by balancing relevance, factuality, and redundancy under an explicit budget. The framework supports MMR, ILP, and a DPP-inspired log-determinant objective without retraining the generator. Experiments on CNN/DailyMail, Multi-News, FaithBench, and TofuEval show consistent improvements in factuality and source-grounding metrics, especially for multi-document summarization, at the cost of lower reference-overlap scores. Human evaluation further indicates higher perceived consistency, relevance, clarity, and conciseness, with a small reduction in coherence. These results show that decoupling generation from selection provides a model-agnostic mechanism for improving factual grounding. Code is available at https://anonymous.4open.science/r/bcfs-D05E/.

arXiv

LoopMTP: A looped transformer guided by latent multi-token prediction

Behzad Shomali, Markus Frey, David Berghaus, Joachim Koehler, Mehdi Ali

Looped transformers have emerged as a parameter-efficient alternative to scaling depth for strong reasoning. By reusing one stack of layers across $T$ iterations, they attain the effective depth and reasoning capabilities of larger models at a fixed parameter count. Yet existing approaches suffer from latent overthinking and undifferentiated computation, largely because intermediate representations receive no guidance across loops. Multi-token prediction (MTP) supplies exactly the dense, forward-looking supervision the loop is missing. We propose \textsc{LoopMTP}, which links the two through a structural correspondence in latent space: a model that loops $T$ times can anticipate $T$ future tokens. \textsc{LoopMTP} realizes this by softly aligning the hidden state of loop $t$ with the embedding of the token $t$ steps ahead, while a lightweight gate preserves useful information across iterations. \textsc{LoopMTP} improves average accuracy by up to 8.1\% (relative) over the non-looped baseline, with training remaining stable for up to 15 loops.

arXiv

A machine-readable catalogue of the Tsiolkovsky papers (fond 555, Archive of the Russian Academy of Sciences), and a way to measure how well its handwriting can be read

Vladimir Beskorovainyi

The personal archive of Konstantin Tsiolkovsky (1857-1935) is held as fond 555 of the Archive of the Russian Academy of Sciences. The archive scanned the fond and published the images, but with no queryable catalogue, no full-text search and no dataset: the holdings can only be browsed one page at a time. This paper describes a machine-readable catalogue of all 2,019 files and 51,008 scans, a dating for 1,969 files taken from the archive's own descriptions, a page-level classification of every scan into handwriting and typescript, and a machine transcription of the fond in full: all 2,019 files and all 51,008 scans. It also reports a way to measure handwritten-text-recognition accuracy in an archive with no ground truth. Archives of the typewriter era often preserve one text twice, as manuscript and as a typed copy; transcribing both and comparing isolates the reading error, since source and pipeline are identical and only page difficulty differs. Across 1,759 such pairs from 224 files, two readings of a handwritten page agree on a median 37% of words and share a longest verbatim run of a median 10 words; the median is unchanged from the 294 pairs of the first version, on a sample six times larger. On two files that also have a published edition the estimate can be checked against ground truth: it is unbiased to within a percentage point and ranks pages as the truth does (rank correlation 0.92 where the edition is a faithful witness). This bounds use: two variants of one work here share 19% of words, below the rate at which two readings of a single page agree, so the redactions cannot be collated word by word at this quality. That negative result is reported as such, and the constraint is built into the tool.

arXiv

Disentangling Language Modeling and Boundaries

Mykola Haltiuk

Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a different, structural advantage: because they read and write bytes, any two of them share an output space, so knowledge transfer between them is exact and independent of how either was originally tokenized. We hypothesize that the two distributions a byte-level model produces, one over the next byte, one over where its patch boundaries fall, can be disentangled and changed almost independently. A model could absorb a teacher's capability while keeping its own boundaries, or change how it places those boundaries while keeping its capabilities. We lay out the two experiments that would settle the hypothesis, alongside preliminary measurements of the properties they rest on. We argue that the community should move toward a byte-level interface as a shared standard: if the hypothesis holds, then once byte-level models are the norm, transferring capabilities and reshaping boundaries between them become cheap and routine, free of the per-model tokenizer that blocks them today.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.