arXiv:2603.25489v1 Announce Type: new
Abstract: Recent strategies for low-resource machine translation rely on LLMs to generate synthetic data from higher-resource languages. We find that this method fails for Romansh, because LLMs tend to confuse its…
arXiv:2506.02533v2 Announce Type: replace
Abstract: Political online participation in the form of discussing political issues and exchanging opinions among citizens is gaining importance with more and more formats being held digitally. To come to a de…
arXiv:2509.16889v3 Announce Type: replace
Abstract: Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement lear…
arXiv:2509.24296v2 Announce Type: replace
Abstract: The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from their iterative and p…
arXiv:2603.25681v1 Announce Type: new
Abstract: As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in scalability. As models approach human-level capabilitie…
arXiv:2510.11233v2 Announce Type: replace
Abstract: Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce and largely focus on binary classification. To addre…
arXiv:2511.21740v4 Announce Type: replace
Abstract: Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes befo…
arXiv:2601.00216v2 Announce Type: replace
Abstract: Current medical retrieval-augmented generation (RAG) approaches overlook evidence-based medicine (EBM) principles, leading to two key gaps: (1) the lack of PICO alignment between queries and retrieve…
arXiv:2603.24709v1 Announce Type: cross
Abstract: Multi-step tool orchestration, where LLMs must invoke multiple dependent APIs in the correct order while propagating intermediate outputs, remains challenging. State-of-the-art models frequently fail o…
arXiv:2603.24755v1 Announce Type: cross
Abstract: Software development is iterative, yet agentic coding benchmarks overwhelmingly evaluate single-shot solutions against complete specifications. Code can pass the test suite but become progressively har…