Search Results for author:
Found 18 papers, 17 papers with code
Efficient Hyper-parameter Search for Knowledge Graph Embedding
Based on the analysis, we propose an efficient two-stage search algorithm KGTuner, which efficiently explores HP configurations on small subgraph at the first stage and transfers the top-performed configurations for fine-tuning on the large full graph at the second stage.
Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
We showcase this advantage by adapting our tool to a lightweight verifier that evaluates the correctness of reasoning paths.
Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements.
Noisy Test-Time Adaptation in Vision-Language Models
Leveraging the zero-shot capability of pre-trained vision-language models (VLMs), this paper introduces Zero-Shot Noisy TTA (ZS-NTTA), focusing on adapting the model to target data with noisy samples during test-time in a zero-shot manner.
Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
In SCIE, the instructions are treated as the treatment, and textual features are used to process natural language, establishing causal relationships through treatments between instructions and downstream tasks.
Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge.
Model Inversion Attacks: A Survey of Approaches and Countermeasures
These attacks highlight the vulnerability of neural networks and raise awareness about the risk of privacy leakage within the research community.
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Here, we propose the method of contrastive denoising with noisy chain-of-thought (CD-CoT).
Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
However, in this paper, we find that there naturally exists a gap, which resembles the modality gap, between the prototype and image instance embeddings extracted from the frozen pre-trained backbone, and simply applying the same transformation during the adaptation phase constrains exploring the optimal representations and shrinks the gap between prototype and image representations.
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
In this paper, we propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to Envision potential Outlier Exposure, termed EOE, without access to any actual OOD data.
Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
To deduce new facts on a knowledge graph (KG), a link predictor learns from the graph structure and collects local evidence to find the answer to a given query.
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails.
Combating Bilateral Edge Noise for Robust Link Prediction
To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse.
Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
To tackle this issue, we propose a method to abstract the collective information of atomic groups into a few $\textit{Neural Atoms}$ by implicitly projecting the atoms of a molecular.
Understanding Fairness Surrogate Functions in Algorithmic Fairness
To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem.
On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored.
AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning
An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step.
KGTuner: Efficient Hyper-parameter Search for Knowledge Graph Learning
While hyper-parameters (HPs) are important for knowledge graph (KG) learning, existing methods fail to search them efficiently.
