Search Results for author:
Found 43 papers, 17 papers with code
Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
Large Language Models (LLMs) have achieved impressive capabilities in language understanding and generation, yet they continue to underperform on knowledge-intensive reasoning tasks due to limited access to structured context and multi-hop information.
AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
Assessing Large Language Models (LLMs)' underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases.
Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
Through extensive experiments, we demonstrate that: 1) CSI effectively captures nuanced emotional patterns, revealing significant variation in LLMs across languages and contexts; 2) Compared to current approaches, CSI significantly improves reliability, yielding more consistent results; and 3) The correlation between CSI scores and the sentiment of LLM's real-world outputs exceeds 0. 85, demonstrating its strong validity in predicting LLM behavior.
Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
The advent of Large Language Models (LLMs) has ushered in an affordable way of leveraging the semantic cues for knowledge-driven causal discovery, but the development of LLMs for causal discovery lags behind other areas, particularly in the exploration of multi-modal data.
Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networks
To bridge this gap, we introduce a novel digital twin-assisted optimization framework, called D-REC, which integrates reinforcement learning (RL) with diverse intervention modules to ensure reliable caching in nextG wireless networks.
Adaptive Draft-Verification for Efficient Large Language Model Decoding
Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities.
DALD: Improving Logits-based Detector without Logits from Black-box LLMs
However, these methods grapple with the misalignment between the distributions of the surrogate and the often undisclosed target models, leading to performance degradation, particularly with the introduction of new, closed-source models.
Embracing Unknown Step by Step: Towards Reliable Sparse Training in Real World
Sparse training has emerged as a promising method for resource-efficient deep neural networks (DNNs) in real-world applications.
On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns.
ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph
While achieving remarkable progress in a broad range of tasks, large language models (LLMs) remain significantly limited in properly using massive external tools.
Students' Perceptions and Preferences of Generative Artificial Intelligence Feedback for Programming
This study demonstrated that ChatGPT could generate Java programming assignment feedback that students perceived as formative.
FP8-BERT: Post-Training Quantization for Transformer
Transformer-based models, such as BERT, have been widely applied in a wide range of natural language processing tasks.
Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models
The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models.
Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection
It is widely acknowledged that large and sparse models have higher accuracy than small and dense models under the same model size constraints.
AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation
Unlike typical adaptive computation challenges that deal with single-step generation problems, diffusion processes with a multi-step generation need to dynamically adjust their computational resource allocation based on the ongoing assessment of each step's importance to the final image output, presenting a unique set of challenges.
Gentopia: A Collaborative Platform for Tool-Augmented LLMs
We present gentopia, an ALM framework enabling flexible customization of agents through simple configurations, seamlessly integrating various language models, task formats, prompting modules, and plugins into a unified paradigm.
Rethinking Data Distillation: Do Not Overlook Calibration
Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods.
Towards Reliable Rare Category Analysis on Graphs via Individual Calibration
In particular, to quantify the uncertainties in RCA, we develop a node-level uncertainty quantification algorithm to model the overlapping support regions with high uncertainty; to handle the rarity of minority classes in miscalibration calculation, we generalize the distribution-based calibration metric to the instance level and propose the first individual calibration measurement on graphs named Expected Individual Calibration Error (EICE).
AutoST: Training-free Neural Architecture Search for Spiking Transformers
To address these limitations, we introduce AutoST, a training-free NAS method for Spiking Transformers, to rapidly identify high-performance Spiking Transformer architectures.
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution.
Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration
Experimental results show that NDSNN achieves up to 20. 52\% improvement in accuracy on Tiny-ImageNet using ResNet-19 (with a sparsity of 99\%) as compared to other SOTA methods (e. g., Lottery Ticket Hypothesis (LTH), SET-SNN, RigL-SNN).
Time Series Contrastive Learning with Information-Aware Augmentations
A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations.
Efficient Informed Proposals for Discrete Distributions via Newton's Series Approximation
Gradients have been exploited in proposal distributions to accelerate the convergence of Markov chain Monte Carlo algorithms on discrete distributions.
Calibrating the Rigged Lottery: Making All Tickets Reliable
Previous research has shown that deep neural networks tend to be over-confident, and we find that sparse training exacerbates this problem.
Balance is Essence: Accelerating Sparse Training via Adaptive Gradient Correction
To accelerate and stabilize the convergence of sparse training, we analyze the gradient changes and develop an adaptive gradient correction method.
Accelerating Dataset Distillation via Model Augmentation
Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones.
Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off
We further design an acquisition function and provide the theoretical guarantees for the proposed method and clarify its convergence property.
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model
To handle this challenge, we propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously in term of input layer-wise similarities with multiple times of early exiting, namely \textbf{MuE}.
A Survey for Efficient Open Domain Question Answering
Thus, a trade-off between accuracy, memory consumption and processing speed is pursued.
S4: a High-sparsity, High-performance AI Accelerator
And the degree of sparsity one can exploit has become higher as larger model sizes have been considered along with the trend of pre-training giant models.
An Automatic and Efficient BERT Pruning for Edge AI Systems
On MRPC, we obtain a 4. 6 higher score than the SOTA at the same overall pruning ratio of 0. 5.
AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models
Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (K=3 for typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e. g., self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training.
InfoGCL: Information-Aware Graph Contrastive Learning
The key point of this framework is to follow the Information Bottleneck principle to reduce the mutual information between contrastive parts while keeping task-relevant information intact at both the levels of the individual module and the entire framework so that the information loss during graph representation learning can be minimized.
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm
Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit.
Information-Aware Time Series Meta-Contrastive Learning
How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question.
Data Augmentation with Adversarial Training for Cross-Lingual NLI
Due to recent pretrained multilingual representation models, it has become feasible to exploit labeled data from one language to train a cross-lingual model that can then be applied to multiple new languages.
Cross-Lingual Natural Language Inference
Data Augmentation
+1
Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm
In particular, common wisdom in pruning CNN states that sparse pruning technique compresses a model more than that obtained by reducing number of channels and layers (Elsen et al., 2020; Zhu and Gupta, 2017), while existing works on sparse pruning of BERT yields inferior results than its small-dense counterparts such as TinyBERT (Jiao et al., 2020).
Parameterized Explainer for Graph Neural Network
The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to a lack of generalizability and hindering it from being used in the inductive setting.
Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification
The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language.
Longitudinal Deep Kernel Gaussian Process Regression
Specifically, L-DKGPR eliminates the need for ad hoc heuristics or trial and error using a novel adaptation of deep kernel learning that combines the expressive power of deep neural networks with the flexibility of non-parametric kernel methods.
How Do We Move: Modeling Human Movement with System Dynamics
To the best of our knowledge, we are the first to learn to model the state transition of moving agents with system dynamics.
LMLFM: Longitudinal Multi-Level Factorization Machine
However, the current state-of-the-art methods are unable to select the most predictive fixed effects and random effects from a large number of variables, while accounting for complex correlation structure in the data and non-linear interactions among the variables.
PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning
To the end, we propose a positive instance detection via graph updating for multiple instance learning, called PIGMIL, to detect TPI accurately.
