1061 papers
The paper proposes AdaCultureSafe, a framework that addresses the lack of correlation between cultural safety and knowledge in Large Language Models by constructing a novel dataset of culturally grounded queries and introducing a knowledge-integrated method to significantly enhance adaptive cultural safety.
This paper evaluates LLM-based grant proposal reviews using structured perturbations on six quality axes, finding that a section-by-section analysis approach outperforms other architectures but that current models still struggle with clarity detection and holistic assessment, suggesting they are best suited as supplementary tools rather than replacements for human reviewers.
This paper introduces SBARThez, a novel framework that leverages multimodal and multilingual sentence embeddings alongside a Named Entity Injection mechanism to enhance the factual consistency and cross-lingual capabilities of abstractive summarization for both text and speech inputs.
This paper introduces LAMUS, a large-scale, high-quality sentence-level legal argument mining corpus for U.S. caselaw constructed via an LLM-driven pipeline with human refinement, which demonstrates that chain-of-thought prompting and LLM-assisted verification significantly enhance annotation quality and model performance for future legal NLP research.
This paper proposes a unified post-training framework that extends speech foundation models to generate multiple arbitrary utterance-level attribute representations, demonstrating its effectiveness through the joint learning of semantic and speaker embeddings for multilingual retrieval and speaker recognition tasks.
This paper introduces SlowBA, a novel backdoor attack against VLM-based GUI agents that utilizes a two-stage reward-level injection strategy and realistic pop-up triggers to induce excessive reasoning chains, thereby significantly increasing response latency while maintaining task accuracy and evading existing defenses.
SPD-RAG is a hierarchical multi-agent framework that improves scalability and answer quality for complex cross-document queries by assigning dedicated agents to process individual documents and synthesizing their outputs through a token-bounded coordinator, achieving superior performance on the LOONG benchmark with significantly reduced API costs compared to standard RAG and full-context baselines.
This paper proposes replacing the dense output projection in multi-head attention with a parameter-free Walsh-Hadamard Transform and lightweight affine rescaling, achieving significant reductions in parameters, memory, and inference latency while maintaining or improving model performance across various benchmarks.
This paper introduces a diagnostic dataset and evaluation framework to investigate how language models handle the proviso problem in pragmatics, revealing that while models align with human judgments, they rely on shallow pattern matching rather than genuine semantic or pragmatic reasoning.
This chapter reviews recent computational models demonstrating that self-supervised and visually grounded learning principles can effectively explain early language acquisition from acoustic and audiovisual speech without relying on strong linguistic priors.
This paper introduces a transformer architecture combining adaptive per-layer looping and gated memory banks, demonstrating that while looping primarily enhances mathematical reasoning and memory aids commonsense tasks, their integration yields a model that outperforms significantly deeper baselines on math benchmarks.
This paper introduces QUORUM, a unified evaluation framework, and COACH, an LLM-driven pipeline, to generate and assess personalized health counseling for cancer patients, demonstrating that while stakeholders converge on the system's relevance and quality, they diverge on nuances like tone and error sensitivity, thereby highlighting the critical need for multi-perspective evaluation in trustworthy patient-centered NLP systems.
This paper introduces Token-Conditioned Reinforcement Learning (ToCoRL), a framework that leverages the intrinsic behavioral plasticity of Large Language Models to internalize and stabilize inference-time adaptations, enabling precise control over behavioral modes like switching from reasoning to direct answering without degrading overall capabilities.
The paper introduces Sandpiper, a mixed-initiative system that integrates interactive researcher dashboards with agentic LLMs to enable scalable, privacy-preserving, and rigorous qualitative analysis of large-scale educational discourse while mitigating hallucinations and ensuring methodological consistency.
This paper challenges the stability of human and AI preferences in Reinforcement Learning from Human Feedback (RLHF) by demonstrating that both are susceptible to "choice blindness," where preferences are easily manipulated by context and shallow cues, leading to undetected reward signal corruption and downstream policy degradation.
This paper proposes a method to equip LLM agents with native retrieval capabilities by projecting their hidden states directly into the embedding space via a lightweight head, thereby eliminating the need for a separate embedding model while retaining 97% of baseline retrieval quality.
This paper introduces VET-Bench, a diagnostic benchmark revealing that current Vision-Language Models fail at tracking visually identical objects due to an over-reliance on static features, and proposes Spatiotemporal Grounded Chain-of-Thought (SGCoT) to achieve over 90% accuracy by explicitly generating object trajectories as intermediate reasoning steps.
This prospective feasibility study demonstrates that a conversational AI system (AMIE) can safely and effectively conduct clinical history-taking and generate diagnostic suggestions in a real-world urgent care setting, achieving high patient satisfaction and diagnostic accuracy comparable to primary care providers while requiring no real-time human intervention.
This paper introduces the first freely available English-to-Swedish dataset designed to benchmark language models' tendency to prefer literal "translationese" over idiomatic phrasing, revealing that exposure to source text biases models toward unnatural translations even when context is removed.
LycheeCluster is a novel KV cache management method that employs structure-aware chunking and hierarchical indexing to transform cache retrieval into a logarithmic-time process, achieving up to a 3.6x inference speedup with minimal performance degradation for long-context LLMs.