Search Results for author:
Found 19 papers, 9 papers with code
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
We will release our dataset, codes, and models to help future efforts in this domain.
Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
In this paper, we deeply explore the mechanisms employed by Transformer-based language models in factual recall tasks.
AS-ES Learning: Towards Efficient CoT Learning in Small Models
Chain-of-Thought (CoT) serves as a critical emerging ability in LLMs, especially when it comes to logical reasoning.
PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks
While physics-informed neural networks (PINNs) have become a popular deep learning framework for tackling forward and inverse problems governed by partial differential equations (PDEs), their performance is known to degrade when larger and deeper neural network architectures are employed.
LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering
Experimental implementations were conducted under constrained computational and memory resources, evaluating the proposed method's performance on benchmark datasets including GQA, CLEVR, and VizWiz-VQA-Grounding.
Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples.
Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
The jailbreak idea of our method is "Inherent Response Tendency Analysis" which identifies real-world instructions that can inherently induce LLMs to generate affirmation responses and the corresponding jailbreak strategy is "Real-World Instructions-Driven Jailbreak" which involves strategically splicing real-world instructions identified through the above analysis around the malicious instruction.
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
Specifically, the crucial information in the context will be potentially overlooked by model when it is positioned in the trough zone of the attention waveform, leading to decreased performance.
Ranked #2 on
Trajectory Planning
on ToolBench
Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse
Recent studies have highlighted a phenomenon in large language models (LLMs) known as "the reversal curse," in which the order of knowledge entities in the training data biases the models' comprehension.
Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
Through extensive experiments on five reasoning datasets from the ERASER benchmark, we demonstrate that our framework not only establishes a more reliable link between the generated rationale and model decision but also achieves competitive results in task performance and the quality of rationale.
From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
Furthermore, our method shows a sustained improvement as the volume of pseudo data increases, revealing the great potential of pseudo data in advancing low-resource cross-modal molecule discovery.
GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue
To address this issue, it is crucial to analyze and mitigate the influence of superficial clues on STM models.
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
To address this challenge, we propose knowledge-tuning, which leverages structured medical knowledge bases for the LLMs to grasp domain knowledge efficiently and facilitate reliable response generation.
DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations
In open-domain dialogue generation tasks, contexts and responses in most datasets are one-to-one mapped, violating an important many-to-many characteristic: a context leads to various responses, and a response answers multiple contexts.
LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
Motivated by it, we propose to use the local similarity (LocalSim) to learn node-level weighted fusion, which can also serve as a plug-and-play module.
Large region targets observation scheduling by multiple satellites using resampling particle swarm optimization
A greedy initialization-based resampling particle swarm optimization (GI-RPSO) algorithm is proposed to solve the model.
Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems
In this study, we propose a model that learns the symplectic form from data using neural networks, thereby providing a method for learning Hamiltonian equations from data represented in general coordinate systems, which are not limited to the generalized coordinates and the generalized momenta.
KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss
To apply the KAM theory, we provide a generalization error bound for Hamiltonian neural networks by deriving an estimate of the covering number of the gradient of the multi-layer perceptron, which is the key ingredient of the model.
Bayesian graphical compositional regression for microbiome data
An important task in microbiome studies is to test the existence of and give characterization to differences in the microbiome composition across groups of samples.
Methodology Applications Computation
