Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.
arXiv:2608.30758v1 Announce Type: new Abstract: Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal r...
AdaFuse is an adaptive ensemble decoding framework for large language models that dynamically selects fusion units during generation. It uses an uncertainty-based criterion to decide when to ensemble, applying a diversity-aware scaling strategy in uncertain states while continuing direct generation when confident. Experiments on question answering, arithmetic reasoning, and machine translation show AdaFuse outperforms strong baselines with an average relative improvement of 6.88%.
The paper investigates the issue of self‑bias when large language models (LLMs) generate and evaluate their own benchmarks. Using machine translation as a testbed, it shows that LLMs as both test‑set creators and evaluators produce model‑specific, homogeneous outputs that inflate their own scores, even when diversity controls are applied. The bias is strong enough that each model ranks itself first, overriding peer consensus, and the phenomenon also appears in open‑ended generation tasks.
arXiv:2608.30372v1 Announce Type: new Abstract: As Large Language Models rapidly advance, performance on standard multiple-choice question answering (MCQA) benchmarks is reaching saturation. While th...
arXiv:2608.28707v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with quest...
arXiv:2512.07571v3 Announce Type: replace Abstract: This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tune...
arXiv:2608.30107v1 Announce Type: cross Abstract: Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and i...
arXiv:2608.30425v1 Announce Type: new Abstract: Cross-lingual aspect-based sentiment analysis (ABSA) transfers knowledge from a source language with annotated data to a target language, enabling fine...
arXiv:2608.30297v1 Announce Type: new Abstract: Attributes describing data content and context can induce diverse imbalance patterns that go beyond label imbalance alone. However, existing studies pr...
arXiv:2605.28740v2 Announce Type: replace-cross Abstract: As large language models are increasingly deployed for clinical text, ensuring they can reliably signal their own uncertainty becomes critica...
arXiv:2608.29037v1 Announce Type: cross Abstract: Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of Multimod...
arXiv:2608.30163v1 Announce Type: cross Abstract: Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, ex...
arXiv:2608.28635v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their...
arXiv:2604.19782v2 Announce Type: replace-cross Abstract: Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LAL...
arXiv:2608.28667v1 Announce Type: cross Abstract: The rapid proliferation of Large Language Models (LLMs) has raised concerns about their environmental impact during inference. While Green AI researc...
arXiv:2608.29890v1 Announce Type: new Abstract: Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information ext...
arXiv:2608.28642v1 Announce Type: new Abstract: Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admit...
arXiv:2502.00857v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly provide direct answers to user questions, raising concerns about reduced engagement in critical thinking...
arXiv:2608.28647v1 Announce Type: new Abstract: Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before a...
arXiv:2608.28608v1 Announce Type: cross Abstract: Ancient Indian medical texts like Sushruta Samhita have extensive information on diseases, treatments, and surgical techniques. Yet, their ancient fo...