arXiv subjects

Guanhua Chen

Publications and source records attributed to Guanhua Chen.

At least 109 records · Page 6Linked to original sources

arXiv2024

Understanding Particles From Video: Property Estimation of Granular Materials via Visuo-Haptic Learning

Granular materials (GMs) are ubiquitous in daily life. Understanding their properties is also important, especially in agriculture and industry. However, existing works require dedicated measurement equipment and also need large human efforts to handle a large number of particles. In this paper, we introduce a method for estimating the relative values of particle size and density from the video of the interaction with GMs. It is trained on a visuo-haptic learning framework inspired by a contact model, which reveals the strong correlation between GM properties and the visual-haptic data during the probe-dragging in the GMs. After training, the network can map the visual modality well to the haptic signal and implicitly characterize the relative distribution of particle properties in its latent embeddings, as interpreted in that contact model. Therefore, we can analyze GM properties using the trained encoder, and only visual information is needed without extra sensory modalities and human efforts for labeling. The presented GM property estimator has been extensively validated via comparison and ablation experiments. The generalization capability has also been evaluated and a real-world application on the beach is also demonstrated. Experiment videos are available at \url{https://sites.google.com/view/gmwork/vhlearning} .

cs.CV↗

arXiv2024

MCCE: Missingness-aware Causal Concept Explainer

Causal concept effect estimation is gaining increasing interest in the field of interpretable machine learning. This general approach explains the behaviors of machine learning models by estimating the causal effect of human-understandable concepts, which represent high-level knowledge more comprehensibly than raw inputs like tokens. However, existing causal concept effect explanation methods assume complete observation of all concepts involved within the dataset, which can fail in practice due to incomplete annotations or missing concept data. We theoretically demonstrate that unobserved concepts can bias the estimation of the causal effects of observed concepts. To address this limitation, we introduce the Missingness-aware Causal Concept Explainer (MCCE), a novel framework specifically designed to estimate causal concept effects when not all concepts are observable. Our framework learns to account for residual bias resulting from missing concepts and utilizes a linear predictor to model the relationships between these concepts and the outputs of black-box machine learning models. It can offer explanations on both local and global levels. We conduct validations using a real-world dataset, demonstrating that MCCE achieves promising performance compared to state-of-the-art explanation methods in causal concept effect estimation.

cs.LG↗

arXiv2024

Position Paper On Diagnostic Uncertainty Estimation from Large Language Models: Next-Word Probability Is Not Pre-test Probability

Large language models (LLMs) are being explored for diagnostic decision support, yet their ability to estimate pre-test probabilities, vital for clinical decision-making, remains limited. This study evaluates two LLMs, Mistral-7B and Llama3-70B, using structured electronic health record data on three diagnosis tasks. We examined three current methods of extracting LLM probability estimations and revealed their limitations. We aim to highlight the need for improved techniques in LLM confidence estimation.

cs.AI↗

arXiv2024

SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation

Out-of-distribution (OOD) detection is crucial for the safe deployment of neural networks. Existing CLIP-based approaches perform OOD detection by devising novel scoring functions or sophisticated fine-tuning methods. In this work, we propose SeTAR, a novel, training-free OOD detection method that leverages selective low-rank approximation of weight matrices in vision-language and vision-only models. SeTAR enhances OOD detection via post-hoc modification of the model's weight matrices using a simple greedy search algorithm. Based on SeTAR, we further propose SeTAR+FT, a fine-tuning extension optimizing model performance for OOD detection tasks. Extensive evaluations on ImageNet1K and Pascal-VOC benchmarks show SeTAR's superior performance, reducing the relatively false positive rate by up to 18.95% and 36.80% compared to zero-shot and fine-tuning baselines. Ablation studies further validate SeTAR's effectiveness, robustness, and generalizability across different model backbones. Our work offers a scalable, efficient solution for OOD detection, setting a new state-of-the-art in this area.

cs.CL↗

arXiv2024

Distract Large Language Models for Automatic Jailbreak Attack

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as jailbreaking, leading to unintended behaviors. In this work, we propose a novel black-box jailbreak framework for automated red teaming of LLMs. We designed malicious content concealing and memory reframing with an iterative optimization algorithm to jailbreak LLMs, motivated by the research about the distractibility and over-confidence phenomenon of LLMs. Extensive experiments of jailbreaking both open-source and proprietary LLMs demonstrate the superiority of our framework in terms of effectiveness, scalability and transferability. We also evaluate the effectiveness of existing jailbreak defense methods against our attack and highlight the crucial need to develop more effective and practical defense strategies.

cs.CR↗

arXiv2024

FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only

Instruction fine-tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets has traditionally been expensive and laborious, often relying on manual annotations or costly API calls of proprietary LLMs. To address these challenges, we introduce FANNO, a fully autonomous, open-sourced framework that revolutionizes the annotation process without the need for pre-existing annotated data. Utilizing a Mistral-7b-instruct model, FANNO efficiently produces diverse and high-quality datasets through a structured process involving document pre-screening, instruction generation, and response generation. Experiments on Open LLM Leaderboard and AlpacaEval benchmark show that the FANNO can generate high-quality data with diversity and complexity for free, comparable to human-annotated or cleaned datasets like Alpaca-GPT4-Cleaned.

cs.CL↗

arXiv2024

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning

Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data. Previous work proposes in-context instruction tuning (ICIT) where specific positive or negative examples are incorporated into the prompt for better performance. In this work, we propose PACIT, a simple and effective in-context instruction tuning method, inspired by the pedagogical concept of desirable difficulty. The PACIT method unlocks the power of examples by encouraging the model to actively learn to grasp the distinctions between the positive and negative examples instead of merely reading. The model is expected to first verify the correctness of the provided example according to the task description, which is then set as the condition for generating a better response to the task instance. Our extensive experiments prove the effectiveness of PACIT, outperforming ICIT baseline on both in-domain and out-domain tasks up to 9.16 and 3.14 average ROUGE-L scores, respectively. Moreover, PACIT can notably enhance the performance of instruction tuning even when all positive and negative examples are generated with a self-instruct method.

cs.CL↗

arXiv2024

A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU

Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin between different multi-intent labels, they are less suited to the nuances of multi-intent NLU. They ignore the rich information between the shared intents, which is beneficial to constructing a better embedding space, especially in low-data scenarios. We introduce a two-stage Prediction-Aware Contrastive Learning (PACL) framework for multi-intent NLU to harness this valuable knowledge. Our approach capitalizes on shared intent information by integrating word-level pre-training and prediction-aware contrastive fine-tuning. We construct a pre-training dataset using a word-level data augmentation strategy. Subsequently, our framework dynamically assigns roles to instances during contrastive fine-tuning while introducing a prediction-aware contrastive loss to maximize the impact of contrastive learning. We present experimental results and empirical analysis conducted on three widely used datasets, demonstrating that our method surpasses the performance of three prominent baselines on both low-data and full-data scenarios.

cs.CL↗

arXiv2023

Strange memory effect of low-field microwave absorption in copper-substituted lead apatite

We observe a considerable hysteresis effect of low-field microwave absorption (LFMA) in copper-substituted lead apatite. By continuously rotating samples under external magnetic field, this effect is diminished which can not be renewed by a strong magnetic field but will be spontaneously recovered after two days, indicating its glassy features and excluding possibility of any ferromagnetism. The intensity of LFMA is found to sharply decrease at around 250K, suggesting a phase transition takes place. A lattice gauge model is then employed to assign these effects to the transition between superconducting Meissner phase and vortex glass, and the slow dynamics wherein is calculated as well.

cond-mat.supr-con↗

arXiv2023

Directing entanglement spreading by means of a quantum East/West heterojunction structure

We extend the translationally invariant quantum East model to an inhomogeneous chain with East/West heterojunction structure. In analogy to the quantum diffusion of substantial particles, we observe a cyclic entanglement entropy spreading in the heterojunction during time evolution, which can be regarded as continuous cycles in a quantum heat engine. In order to figure out the possibility of manipulating the entanglement entropy as a quantum resource, the entropy growth is shown to be determined by the initial occupation and the site-dependent chemical potential, and the former is equivalent to an effective temperature. Through fine adjustment of these parameters, we discover the entanglement flow is simply superposed with those from two sources of the chain. An intriguing relation between our model and the traditional heat engines is subsequently established.

quant-ph↗

arXiv2023

StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation

Stylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users. As style-specific article-headline pairs are scarce, previous researches focus on unsupervised approaches with a standard headline generation dataset and mono-style corpora. In this work, we follow this line and propose StyleBART, an unsupervised approach for stylistic headline generation. Our method decorates the pretrained BART model with adapters that are responsible for different styles and allows the generation of headlines with diverse styles by simply switching the adapters. Different from previous works, StyleBART separates the task of style learning and headline generation, making it possible to freely combine the base model and the style adapters during inference. We further propose an inverse paraphrasing task to enhance the style adapters. Extensive automatic and human evaluations show that StyleBART achieves new state-of-the-art performance in the unsupervised stylistic headline generation task, producing high-quality headlines with the desired style.

cs.CL↗

arXiv2023

A reluctant additive model framework for interpretable nonlinear individualized treatment rules

Individualized treatment rules (ITRs) for treatment recommendation is an important topic for precision medicine as not all beneficial treatments work well for all individuals. Interpretability is a desirable property of ITRs, as it helps practitioners make sense of treatment decisions, yet there is a need for ITRs to be flexible to effectively model complex biomedical data for treatment decision making. Many ITR approaches either focus on linear ITRs, which may perform poorly when true optimal ITRs are nonlinear, or black-box nonlinear ITRs, which may be hard to interpret and can be overly complex. This dilemma indicates a tension between interpretability and accuracy of treatment decisions. Here we propose an additive model-based nonlinear ITR learning method that balances interpretability and flexibility of the ITR. Our approach aims to strike this balance by allowing both linear and nonlinear terms of the covariates in the final ITR. Our approach is parsimonious in that the nonlinear term is included in the final ITR only when it substantially improves the ITR performance. To prevent overfitting, we combine cross-fitting and a specialized information criterion for model selection. Through extensive simulations, we show that our methods are data-adaptive to the degree of nonlinearity and can favorably balance ITR interpretability and flexibility. We further demonstrate the robust performance of our methods with an application to a cancer drug sensitive study.

stat.ME↗

arXiv2023

Long-coherence pairing of low-mass conduction electrons in copper-substituted lead apatite

Two entangled qubits emerge as an essential resource for quantum control, which are normally quantum confined with atomic precision. It seems inhibitive that in the macroscopic scope collective qubit pairs manifest long coherence and quantum entanglement, especially at high temperature. Here, we report this exotic ensemble effect in solid-state sintering lead apatite samples with copper substitution, which have been repeatedly duplicated with superior stability and low cost. An extraordinarily low-field absorption signal of cw electron paramagnetic resonance (EPR) spectroscopy stems from low-mass conduction electrons implying the coherence of cuprate radicals can be long-termly protected. The pulsed EPR experiments exhibit triplet Rabi oscillation from paired cuprate diradicals with the coherence time exceeding 1 microsecond at 85K. We believe these appealing effects are sufficiently promising to be applied for scalable quantum control and computation.

quant-ph↗

arXiv2023

Minimum Resource Threshold Policy Under Partial Interference

When developing policies for prevention of infectious diseases, policymakers often set specific, outcome-oriented targets to achieve. For example, when developing a vaccine allocation policy, policymakers may want to distribute them so that at least a certain fraction of individuals in a census block are disease-free and spillover effects due to interference within blocks are accounted for. The paper proposes methods to estimate a block-level treatment policy that achieves a pre-defined, outcome-oriented target while accounting for spillover effects due to interference. Our policy, the minimum resource threshold policy (MRTP), suggests the minimum fraction of treated units required within a block to meet or exceed the target level of the outcome. We estimate the MRTP from empirical risk minimization using a novel, nonparametric, doubly robust loss function. We then characterize statistical properties of the estimated MRTP in terms of the excess risk bound. We apply our methodology to design a water, sanitation, and hygiene allocation policy for Senegal with the goal of increasing the proportion of households with no children experiencing diarrhea to a level exceeding a specified threshold. Our policy outperforms competing policies and offers new approaches to design allocation policies, especially in international development for communicable diseases.

stat.AP↗

arXiv2023

Evaluating Explanation Methods for Vision-and-Language Navigation

The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of vision-and-language navigation (VLN), it is equally interesting to know what information the models utilize for their decision-making in the navigation tasks. To understand the inner workings of deep neural models, various explanation methods have been developed for promoting explainable AI (XAI). But they are mostly applied to deep neural models for image or text classification tasks and little work has been done in explaining deep neural models for VLN tasks. In this paper, we address these problems by building quantitative benchmarks to evaluate explanation methods for VLN models in terms of faithfulness. We propose a new erasure-based evaluation pipeline to measure the step-wise textual explanation in the sequential decision-making setting. We evaluate several explanation methods for two representative VLN models on two popular VLN datasets and reveal valuable findings through our experiments.

cs.RO↗

arXiv2023

Robust Sample Weighting to Facilitate Individualized Treatment Rule Learning for a Target Population

Learning individualized treatment rules (ITRs) is an important topic in precision medicine. Current literature mainly focuses on deriving ITRs from a single source population. We consider the observational data setting when the source population differs from a target population of interest. Compared with causal generalization for the average treatment effect which is a scalar quantity, ITR generalization poses new challenges due to the need to model and generalize the rules based on a prespecified class of functions which may not contain the unrestricted true optimal ITR. The aim of this paper is to develop a weighting framework to mitigate the impact of such misspecification and thus facilitate the generalizability of optimal ITRs from a source population to a target population. Our method seeks covariate balance over a non-parametric function class characterized by a reproducing kernel Hilbert space and can improve many ITR learning methods that rely on weights. We show that the proposed method encompasses importance weights and overlap weights as two extreme cases, allowing for a better bias-variance trade-off in between. Numerical examples demonstrate that the use of our weighting method can greatly improve ITR estimation for the target population compared with other weighting methods.

stat.ML↗

arXiv2023

Nonthermal entanglement dynamics in a dipole-facilitated glassy model with disconnected subspaces

We construct a dipole-facilitated kinetic constraint to partition the Hilbert space into three disconnected subspaces, two of which are nonthermal and the other acts as an intrinsic thermal bath. The resulting glassy system freely oscillates in nonthermal subspaces, making the quantum entanglement perform like a substantial qubit. The spatially spreading entanglement, quantified by concurrence, fidelity and 2-Rényi entropy, is found to be spontaneously recovered which is absent in other reference models. Under low-frequency random flip noise, this reversible hydrodynamics of entanglement holds high fidelity and volume law, while at high frequency thermalization unusually occurs leading to a strange phase transition. Our work offers an elaborate space structure for realizing ergodicity breaking and controllable entanglement dynamics.

quant-ph↗

arXiv2023

Independence weights for causal inference with continuous treatments

Studying causal effects of continuous treatments is important for gaining a deeper understanding of many interventions, policies, or medications, yet researchers are often left with observational studies for doing so. In the observational setting, confounding is a barrier to the estimation of causal effects. Weighting approaches seek to control for confounding by reweighting samples so that confounders are comparable across different treatment values. Yet, for continuous treatments, weighting methods are highly sensitive to model misspecification. In this paper we elucidate the key property that makes weights effective in estimating causal quantities involving continuous treatments. We show that to eliminate confounding, weights should make treatment and confounders independent on the weighted scale. We develop a measure that characterizes the degree to which a set of weights induces such independence. Further, we propose a new model-free method for weight estimation by optimizing our measure. We study the theoretical properties of our measure and our weights, and prove that our weights can explicitly mitigate treatment-confounder dependence. The empirical effectiveness of our approach is demonstrated in a suite of challenging numerical experiments, where we find that our weights are quite robust and work well under a broad range of settings.

stat.ME↗