Search Results for author:
Found 12 papers, 9 papers with code
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
Exploring Mode Connectivity for Pre-trained Language Models
(3) How does the PLM's task knowledge change along the path connecting two minima?
Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning
To fathom the mystery, we hypothesize that the adaptations of different DETs could all be reparameterized as low-dimensional optimizations in a unified optimization subspace, which could be found by jointly decomposing independent solutions of different DETs.
Deep Deconfounded Content-based Tag Recommendation for UGC with Causal Intervention
We first establish a causal graph to represent the relations among uploader, UGC, and tag, where the uploaders are identified as confounders that spuriously correlate UGC and tag selections.
Multi-Auxiliary Augmented Collaborative Variational Auto-encoder for Tag Recommendation
Recommending appropriate tags to items can facilitate content organization, retrieval, consumption and other applications, where hybrid tag recommender systems have been utilized to integrate collaborative information and content information for better recommendations.
Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models
This necessitates a new branch of research focusing on the parameter-efficient adaptation of PLMs, dubbed as delta tuning in this paper.
QuoteR: A Benchmark of Quote Recommendation for Writing
To facilitate the research on this task, we build a large and fully open quote recommendation dataset called QuoteR, which comprises three parts including English, standard Chinese and classical Chinese.
Deep Causal Reasoning for Recommendations
As with all observational studies, hidden confounders, which are factors that affect both item exposures and user ratings, lead to a systematic bias in the estimation.
Exploring Universal Intrinsic Task Subspace via Prompt Tuning
In the experiments, we study diverse few-shot NLP tasks and surprisingly find that in a 250-dimensional subspace found with 100 tasks, by only tuning 250 free parameters, we can recover 97% and 83% of the full prompt tuning performance for 100 seen tasks (using different training data) and 20 unseen tasks, respectively, showing great generalization ability of the found intrinsic task subspace.
Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation
Moreover, the multimodal information is fused by the product-of-experts (PoE) principle, where the semantic information in visual and textual modalities of the micro-video are weighted according to their variance estimations such that the modality with a lower noise level is given more weights.
Knowledge Inheritance for Pre-trained Language Models
Specifically, we introduce a pre-training framework named "knowledge inheritance" (KI) and explore how could knowledge distillation serve as auxiliary supervision during pre-training to efficiently learn larger PLMs.
