1077 papers
This paper introduces MuSaG, the first German multimodal sarcasm dataset featuring aligned text, audio, and video annotations from television shows, and demonstrates through benchmarking that current models struggle to match human reliance on audio cues, thereby highlighting a critical gap for future multimodal sarcasm detection research.
This paper introduces the Agent Data Protocol (ADP), a lightweight interlingua that unifies fragmented agent datasets across diverse formats into a standardized pipeline, enabling effective large-scale supervised fine-tuning that achieves state-of-the-art performance on various agent benchmarks without domain-specific tuning.
The paper introduces CareMedEval, a novel dataset derived from French medical student exams that evaluates the ability of large language models to perform critical appraisal and reasoning on biomedical literature, revealing significant limitations in current models despite improvements from intermediate reasoning steps.
This paper presents a human-in-the-loop approach using large language models with various prompting strategies to extract Dutch metaphors from cancer patient interviews and forum data, resulting in the creation of the HealthQuote.NL corpus to enhance healthcare communication and personalized care.
This paper demonstrates that appraisal theories, which capture the subjective cognitive evaluations of an argument's impact, are more effective than categorical emotion models in predicting argument convincingness.
This paper presents a case study on developing a Multimodal Large Language Model for the low-resource Basque language, demonstrating that strong performance can be achieved with approximately 20% Basque multimodal data and that a Basque-adapted language model backbone is not strictly necessary.
This paper introduces Dripper, a lightweight framework that reformulates web main content extraction as a constrained sequence labeling task using Small Language Models, achieving superior efficiency and accuracy compared to both traditional heuristics and massive generative LLMs while enabling the creation of high-quality training corpora.
This study employs contrastive explanations and saliency attribution to identify specific source tokens that trigger gender bias in neural machine translation models, revealing a significant overlap between these model-driven triggers and human gender perceptions to inform future bias mitigation strategies.
This paper proposes Non-Resolution Reasoning (NRR), a novel computational framework that challenges the premature ambiguity collapse in current AI by introducing principles of non-identity and parallel interpretation retention to preserve contextual identity and maintain multiple valid meanings until resolution is explicitly required.
This study systematically evaluates four widely adopted large language models across political, ideological, alliance, linguistic, and gender dimensions, revealing that despite alignment efforts for neutrality, these models still exhibit significant biases and affinities.
This paper demonstrates that Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the generalization of causal reasoning in large language models compared to supervised fine-tuning, but only when the models possess sufficient initial reasoning competence and are trained on specific combinations of model scale and query complexity.
This paper introduces DevRev-Search, an automated benchmark for technical support retrieval, and proposes an Index-Preserving Adaptation strategy that fine-tunes only the query encoder to achieve scalable, high-performance multi-tenant search without the prohibitive cost of re-indexing.
This paper introduces a post-training paradigm that leverages knowledge graphs as implicit reward models to guide large language models in learning compositional reasoning from axiomatic facts, enabling a 14B model to outperform frontier systems on complex multi-hop medical queries through path-derived supervision.
This paper introduces NRR-Phi, a formal framework that maps ambiguous text to a non-collapsing state space using a hybrid extraction pipeline, thereby preserving multiple interpretations and preventing premature semantic commitment in large language model inference.
This paper presents the first empirical study on training LLMs to abstain from answering in temporal question answering by combining Chain-of-Thought supervision with Reinforcement Learning, demonstrating that this approach significantly outperforms existing models in accuracy and reliability while revealing the limitations of implicit reasoning cues and supervised fine-tuning.
This paper proposes "Rewards as Labels" (REAL), a novel framework that reformulates Reinforcement Learning with Verifiable Rewards as a classification problem to address gradient misassignment and domination issues in methods like GRPO, thereby achieving superior training stability and performance on mathematical reasoning benchmarks compared to state-of-the-art baselines.
The paper introduces SureLock, a method for Masked Diffusion-LMs that dynamically locks converged token positions to skip redundant computations while caching their keys and values, thereby reducing per-iteration complexity from to and achieving 30–50% FLOP savings without compromising generation quality.
This study reveals that Large Reasoning Models often fail to outperform non-reasoning models in Theory of Mind tasks due to performance degradation from excessive "slow thinking" and reliance on option-matching shortcuts, indicating that robust social reasoning requires capabilities distinct from formal logical deduction.
This paper introduces the first NLP dataset for the endangered Meenzerisch dialect of Mainz and demonstrates that current large language models struggle significantly to generate or define its words, achieving accuracy rates below 10% even with few-shot learning and rule extraction, thereby highlighting an urgent need for further research and resources to preserve German dialects.
This paper introduces a novel Czech restaurant-domain dataset enriched with opinion terms for aspect-based sentiment analysis, benchmarks various Transformer and LLM models across multiple settings, and proposes an LLM-driven translation and label alignment methodology to effectively address cross-lingual challenges in low-resource languages.