5 papers
SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning
Zhu Li, Yongjian Chen, Huiyuan Lai +3
Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning. To enable robust sarcasm reasoning wi…
TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning
Huiyuan Lai, Malvina Nissim
Large Language Models (LLMs) have shown remarkable performance on complex reasoning tasks, especially when equipped with long chain-of-thought (CoT) reasoning. However, eliciting l…
OntoURL: A Benchmark for Evaluating Large Language Models on Symbolic Ontological Understanding, Reasoning and Learning
Xiao Zhang, Huiyuan Lai, Qianru Meng +1
Large language models have demonstrated remarkable capabilities across a wide range of tasks, yet their ability to process structured symbolic knowledge remains underexplored. To a…
Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation
Huiyuan Lai, Esther Ploeger, Rik van Noord +1
Neural machine translation (NMT) systems amplify lexical biases present in their training data, leading to artificially impoverished language in output translations. These language…
Multidimensional Consistency Improves Reasoning in Language Models
Huiyuan Lai, Xiao Zhang, Malvina Nissim
While Large language models (LLMs) have proved able to address some complex reasoning tasks, we also know that they are highly sensitive to input variation, which can lead to diffe…