Search Results for author:
Found 9 papers, 5 papers with code
MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation
This paper proposes a recommender system to alleviate the cold-start problem that can estimate user preferences based on only a small number of items.
Self-Supervised Multimodal Opinion Summarization
To use the abundant information contained in non-text data, we propose a self-supervised multimodal opinion summarization framework called MultimodalSum.
Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representation
The common research goal of self-supervised learning is to extract a general representation which an arbitrary downstream task would benefit from.
GTA: Gated Toxicity Avoidance for LM Performance Preservation
Our findings reveal that gated toxicity avoidance efficiently achieves comparable levels of toxicity reduction to the original CTG methods while preserving the generation performance of the language model.
SQuAD2-CR: Semi-supervised Annotation for Cause and Rationales for Unanswerability in SQuAD 2.0
Existing machine reading comprehension models are reported to be brittle for adversarially perturbed questions when optimizing only for accuracy, which led to the creation of new reading comprehension benchmarks, such as SQuAD 2. 0 which contains such type of questions.
CITIES: Contextual Inference of Tail-Item Embeddings for Sequential Recommendation
To eliminate this issue, we propose a framework called CITIES, which aims to enhance the quality of the tail-item embeddings by training an embedding-inference function using multiple contextual head items so that the recommendation performance improves for not only the tail items but also for the head items.
Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
Motivated by these, we explore the impact of the inherent preference in LLMs on providing emotional support, and consequently, we observe that exhibiting high preference for specific strategies hinders effective emotional support, aggravating its robustness in predicting the appropriate strategy.
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement
We propose self-refine with formatting that achieves outstanding safety even in non-safety-aligned LMs and evaluate our method alongside several defense baselines, demonstrating that it is the safest training-free method against jailbreak attacks.
