10 accepted papers
Emotional support is a core capability in human-AI interaction, with applications including psychological counseling, role play, and companionship. However, existing evaluations of large language models (LLMs) often rely on short, static dialogues and fail to capture the dynamic and long-term nature
Large language models (LLMs) suffer from a lack of decision-making transparency, limiting their deployment in high-stakes domains such as healthcare. We propose a mechanistic interpretability framework that introduces two novel paradigms: Medical Fine-Tuning with Frozen Attention Layers (FTFA) and P
Generative approaches to relational triplet extraction (RTE) developed on the sequence model have effectively handled monotonous relations. However, the nuanced complexities of composite relationships among entities significantly challenge their performance. In this paper, we adapt pre-trained langu…
Abstractive summarization commonly suffers from exposure bias caused by supervised teacher-force learning, that a model predicts the next token conditioned on the accurate pre-context during training while on its preceding outputs at inference. Existing solutions bridge this gap through un- or semi-…
Abstractive summarization models learned with maximum likelihood estimation (MLE) have been proven to produce hallucinatory content, which heavily limits their real-world applicability. Preceding studies attribute this problem to the semantic insensitivity of MLE, and they compensate for it with add…
Abstractive summarization suffers from exposure bias caused by the teacher-forced maximum likelihood estimation (MLE) learning, that an autoregressive language model predicts the next token distribution conditioned on the exact pre-context during training while on its own predictions at inference. P…
Abstractive summarization models learned with maximum likelihood estimation (MLE) have long been guilty of generating unfaithful facts alongside ambiguous focus. Improved paradigm under the guidance of reference-identified words, i.e., guided summarization, has exhibited remarkable advantages in ove…
Existing dialog models are trained with data in an encoder-decoder framework with the same parameters, ignoring the multinomial distribution nature in the dataset. In fact, model improvement and development commonly requires fine-grained modeling on individual data subsets. However, collecting a lab…
Curriculum learning, a machine training strategy that feeds training instances to the model from easy to hard, has been proven to facilitate the dialogue generation task. Meanwhile, knowledge distillation, a knowledge transformation methodology among teachers and students networks can yield signific…
Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise. Existing related methods usually incorporate extra submodels to help filter noise before the noisy data is input to main models…