Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.
arXiv:2609.26208v1 Announce Type: new Abstract: Data visualization is central to analytical reasoning, but real-world analysis increasingly requires language-driven interactive interfaces rather than...
arXiv:2609.26610v1 Announce Type: new Abstract: Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested...
The ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains introduced a new Visual Question Answering benchmark that tests reasoning over documents from eight distinct domains such as business reports, scientific papers, and engineering drawings. Twenty valid submissions from eight teams were evaluated, featuring approaches ranging from zero‑shot vision‑language models to multi‑agent ensembles and fine‑tuned multimodal systems. Results indicate that the most effective systems employ structured evidence extraction, retrieval, verification, and orchestration across multiple components rather than single‑pass prompting.
The paper introduces ufakzeka-1, a 151‑million‑parameter Turkish language model trained from scratch on 13.5 B tokens. It details the tokenizer, a three‑stage pretraining schedule, post‑training data augmentation, and a comprehensive evaluation suite that includes release gates, a rule‑checked conversation sweep, and hand tests—all with prompts excluded from training data. The authors report three key findings about safety gate performance, training‑seed variance, and data‑round effects, and they release the model weights, data recipe, evaluation code, and spend ledger under Apache‑2.0.
The paper introduces Dynamic Tool Output Compression (DTOC), a framework that manages context in large‑language‑model agents by storing full tool outputs in external memory and inserting compact placeholders into the active context. DTOC treats context updates as explicit, reversible operations within the agent’s reasoning loop, allowing selective reconstruction of compressed outputs when needed. Experiments on the DeepSWE benchmark show that for responsive models such as Sonnet 4.6 and GPT‑5.4, DTOC reduces input tokens and agent steps while significantly improving solve rates and lowering cost per solved task, with ablation studies confirming the importance of reversibility for maintaining performance.
The paper introduces a stability and boundary-aware explanation-guided framework for medical named entity recognition (NER) in Chinese atopic dermatitis clinical texts. It uses perturbation-based analysis to assess explanation stability and entity boundary sensitivity, and an adaptive fusion strategy to combine local and global explanations. The fused explanations are integrated into training via stability, boundary-aware, and consistency constraints, leading to improved recognition performance and more reliable explanations across multiple NER models.
The paper introduces WaterBERT, a domain‑adapted encoder model trained on a 2.97‑billion‑token water treatment corpus to capture domain‑specific semantics for literature mining. Fine‑tuned versions of WaterBERT outperform general‑purpose and other domain BERT models on tasks such as treatment process classification, named entity recognition, and relation extraction. The authors also demonstrate WaterBERT’s utility in large‑scale processing, generating coherent research topics, building a structured knowledge graph from 693,211 abstracts, and creating a Water Knowledge‑Enhanced Retrieval System that surpasses text‑based baselines.
The paper introduces ChartBias, a benchmark of 820 real-world charts covering six social attributes, designed to audit bias in vision‑language models (VLMs) that interpret charts. Across 12 VLMs, the study identifies three failure modes—narrative shift, group hallucination, and preference polarity—where models produce different or misleading narratives when the referenced social group changes. A multi‑agent mitigation framework is proposed, separating evidence extraction from group‑conditioned generation and using a counterfactual judge, which reduces narrative shift while maintaining chart‑grounded reasoning.
arXiv:2609.22529v1 Announce Type: new Abstract: International law provides the normative framework through which states coordinate action, regulate armed conflict, and protect human rights, yet its t...
arXiv:2609.24002v1 Announce Type: new Abstract: Large language model agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specifi...
arXiv:2609.22851v2 Announce Type: cross Abstract: Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio...
StableVQ introduces practical guidelines to improve training stability for vector‑quantized tokenizers used in image generation models. It addresses instability caused by the entanglement of encoder–decoder and codebook training by proposing three techniques: Dynamic STE for the encoder, Region VQ Loss for the codebook, and a Decoupled Schedule for independent learning rates. Experiments on ImageNet show consistent gains in stability, codebook utilization, and reconstruction quality across various settings.
arXiv:2609.25008v1 Announce Type: new Abstract: I pretrained a language model end-to-end in Rust - alone, with no team, no PyTorch, and no Python in the training path - for $164 in rented GPU time. I...
arXiv:2609.25853v1 Announce Type: new Abstract: Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be...
arXiv:2609.26468v1 Announce Type: new Abstract: A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability o...
arXiv:2510.17881v4 Announce Type: replace Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We int...
arXiv:2607.14109v2 Announce Type: replace Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central...
arXiv:2409.02244v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used as ad hoc therapists. While prior research has found that LLMs outperform human coun...
Accumulated scientific knowledge advances inquiry when prior findings help researchers choose new questions, design investigations, and interpret results. Realizing this value at scale requires access...
Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adjacent token spans are highly predictable or freque...