arXiv subjects

Hui Liu

Publications and source records attributed to Hui Liu.

At least 271 records · Page 15Linked to original sources

arXiv2025

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains

Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, and search-related data. Then, it prompts the same LLM to generate diverse domain-relevant questions from unlabeled corpora, with an additional filtering strategy to retain high-quality synthetic examples. By leveraging these self-generated synthetic examples, the LLM can improve their performance on domain-specific RAG tasks. Experiments on 11 datasets, spanning two backbone sizes and three domains, demonstrate that SimRAG outperforms baselines by 1.2\%--8.6\%.

cs.CL↗

arXiv2025

Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?

Concise and meaningful method names are crucial for program comprehension and maintenance. However, method names may become inconsistent with their corresponding implementations, causing confusion and errors. Several deep learning (DL)-based approaches have been proposed to identify such inconsistencies, with initial evaluations showing promising results. However, these evaluations typically use a balanced dataset, where the number of inconsistent and consistent names are equal. This setup, along with flawed dataset construction, leads to false positives, making reported performance less reliable in real-world scenarios, where most method names are consistent. In this paper, we present an empirical study that evaluates state-of-the-art DL-based methods for identifying inconsistent method names. We create a new benchmark by combining automatic identification from commit histories and manual developer inspections, reducing false positives. We evaluate five representative DL approaches (one retrieval-based and four generation-based) on this benchmark. Our results show that performance drops substantially when moving from the balanced dataset to the new benchmark. We further conduct quantitative and qualitative analyses to understand the strengths and weaknesses of the approaches. Retrieval-based methods perform well on simple methods and those with popular name sub-tokens but fail due to inefficient representation techniques. Generation-based methods struggle with inaccurate similarity calculations and immature name generation. Based on these findings, we propose improvements using contrastive learning and large language models (LLMs). Our study suggests that significant improvements are needed before these DL approaches can be effectively applied to real-world software systems.

cs.SE↗

arXiv2025

Impact of the phase transition on Quark-Gluon Plasma with an extremely strong magnetic field in holographic QCD

We investigate the phase transition within an extremely strong magnetic background field, employing a holographic Quantum Chromodynamics (QCD) model with a focus on entropy and pressure properties. At relatively modest magnetic field strengths, our study discerns a crossover transition between the normal phase and the Quark-Gluon Plasma (QGP) phase as the temperature rises. In contrast, under the influence of an extremely strong magnetic field, a first-order phase transition is observed. A critical point is identified at $ (eB_c, T_c) \approx (2.8623 \, \text{GeV}^2, 0.1191 \, \text{GeV}) $, which corresponds to a second-order phase transition. This phase structure is found to be in qualitative agreement with lattice simulation predictions reported in [Phys. Rev. D \textbf{105}, 034511 (2022)]. Furthermore, we explore the impact of the magnetic field on the jet quenching parameter across various phases. At zero magnetic field ($ eB = 0$ ), the normalized jet quenching parameter $ \hat{q} / T^3 $ exhibits a monotonic increase with temperature. However, in the presence of a magnetic background field, the normalized jet quenching parameters not only display directional anisotropy but also experience a universal enhancement, particularly in the vicinity of the critical temperature region. This observation suggests that the jet quenching parameter could potentially act as an indicator of phase transitions.

hep-th↗

arXiv2025

Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses

Phenotypic drug discovery has attracted widespread attention because of its potential to identify bioactive molecules. Transcriptomic profiling provides a comprehensive reflection of phenotypic changes in cellular responses to external perturbations. In this paper, we propose XTransferCDR, a novel generative framework designed for feature decoupling and transferable representation learning across domains. Given a pair of perturbed expression profiles, our approach decouples the perturbation representations from basal states through domain separation encoders and then cross-transfers them in the latent space. The transferred representations are then used to reconstruct the corresponding perturbed expression profiles via a shared decoder. This cross-transfer constraint effectively promotes the learning of transferable drug perturbation representations. We conducted extensive evaluations of our model on multiple datasets, including single-cell transcriptional responses to drugs and single- and combinatorial genetic perturbations. The experimental results show that XTransferCDR achieved better performance than current state-of-the-art methods, showcasing its potential to advance phenotypic drug discovery.

cs.LG↗

arXiv2025

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning

Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks; however, they still encounter challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences. This challenge is particularly pronounced in tasks involving multi-step processes, such as logical reasoning and multi-hop question answering, where understanding implicit relationships between entities and leveraging multi-hop connections in the given context are crucial. Graphs, as fundamental data structures, explicitly represent pairwise relationships between entities, thereby offering the potential to enhance LLMs' reasoning capabilities. External graphs have proven effective in supporting LLMs across multiple tasks. However, in many reasoning tasks, no pre-existing graph structure is provided. Can we structure implicit knowledge derived from context into graphs to assist LLMs in reasoning? In this paper, we propose Reasoning with Graphs (RwG) by first constructing explicit graphs from the context and then leveraging these graphs to enhance LLM reasoning performance on reasoning tasks. Extensive experiments demonstrate the effectiveness of the proposed method in improving both logical reasoning and multi-hop question answering tasks.

cs.CL↗

arXiv2025

A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules

The immune checkpoint inhibitors have demonstrated promising clinical efficacy across various tumor types, yet the percentage of patients who benefit from them remains low. The bindings between tumor antigens and HLA-I/TCR molecules determine the antigen presentation and T-cell activation, thereby playing an important role in the immunotherapy response. In this paper, we propose UnifyImmun, a unified cross-attention transformer model designed to simultaneously predict the bindings of peptides to both receptors, providing more comprehensive evaluation of antigen immunogenicity. We devise a two-phase strategy using virtual adversarial training that enables these two tasks to reinforce each other mutually, by compelling the encoders to extract more expressive features. Our method demonstrates superior performance in predicting both pHLA and pTCR binding on multiple independent and external test sets. Notably, on a large-scale COVID-19 pTCR binding test set without any seen peptide in training set, our method outperforms the current state-of-the-art methods by more than 10\%. The predicted binding scores significantly correlate with the immunotherapy response and clinical outcomes on two clinical cohorts. Furthermore, the cross-attention scores and integrated gradients reveal the amino-acid sites critical for peptide binding to receptors. In essence, our approach marks a significant step toward comprehensive evaluation of antigen immunogenicity.

q-bio.BM↗

arXiv2025

Deep Assessment of Code Review Generation Approaches: Beyond Lexical Similarity

Code review is a standard practice for ensuring the quality of software projects, and recent research has focused extensively on automated code review. While significant advancements have been made in generating code reviews, the automated assessment of these reviews remains less explored, with existing approaches and metrics often proving inaccurate. Current metrics, such as BLEU, primarily rely on lexical similarity between generated and reference reviews. However, such metrics tend to underestimate reviews that articulate the expected issues in ways different from the references. In this paper, we explore how semantic similarity between generated and reference reviews can enhance the automated assessment of code reviews. We first present a benchmark called \textit{GradedReviews}, which is constructed by collecting real-world code reviews from open-source projects, generating reviews using state-of-the-art approaches, and manually assessing their quality. We then evaluate existing metrics for code review assessment using this benchmark, revealing their limitations. To address these limitations, we propose two novel semantic-based approaches for assessing code reviews. The first approach involves converting both the generated review and its reference into digital vectors using a deep learning model and then measuring their semantic similarity through Cosine similarity. The second approach generates a prompt based on the generated review and its reference, submits this prompt to ChatGPT, and requests ChatGPT to rate the generated review according to explicitly defined criteria. Our evaluation on the \textit{GradedReviews} benchmark indicates that the proposed semantic-based approaches significantly outperform existing state-of-the-art metrics in assessing generated code review, improving the correlation coefficient between the resulting scores and human scores from 0.22 to 0.47.

cs.SE↗

arXiv2025

Towards generalization of drug response prediction to single cells and patients utilizing importance-aware multi-source domain transfer learning

The advancement of single-cell sequencing technology has promoted the generation of a large amount of single-cell transcriptional profiles, providing unprecedented opportunities to identify drug-resistant cell subpopulations within a tumor. However, few studies have focused on drug response prediction at single-cell level, and their performance remains suboptimal. This paper proposed scAdaDrug, a novel multi-source domain adaptation model powered by adaptive importance-aware representation learning to predict drug response of individual cells. We used a shared encoder to extract domain-invariant features related to drug response from multiple source domains by utilizing adversarial domain adaptation. Particularly, we introduced a plug-and-play module to generate importance-aware and mutually independent weights, which could adaptively modulate the latent representation of each sample in element-wise manner between source and target domains. Extensive experimental results showed that our model achieved state-of-the-art performance in predicting drug response on multiple independent datasets, including single-cell datasets derived from both cell lines and patient-derived xenografts (PDX) models, as well as clinical tumor patient cohorts. Moreover, the ablation experiments demonstrated our model effectively captured the underlying patterns determining drug response from multiple source domains.

cs.AI↗

arXiv2024

Mixture of Link Predictors on Graphs

Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models that only apply the same pairwise information uniformly could achieve suboptimal performance. As a result, we propose a simple mixture of experts model Link-MoE for link prediction. Link-MoE utilizes various GNNs as experts and strategically selects the appropriate expert for each node pair based on various types of pairwise information. Experimental results across diverse real-world datasets demonstrate substantial performance improvement from Link-MoE. Notably, Link-MoE achieves a relative improvement of 18.71\% on the MRR metric for the Pubmed dataset and 9.59\% on the Hits@100 metric for the ogbl-ppa dataset, compared to the best baselines.

cs.LG↗

arXiv2024

Improving image quality of the Solar Disk Imager (SDI) of the Lyman-alpha Solar Telescope (LST) onboard the ASO-S mission

The in-flight calibration and performance of the Solar Disk Imager (SDI), which is a pivotal instrument of the Lyman-alpha Solar Telescope (LST) onboard the Advanced Space-based Solar Observatory (ASO-S) mission, suggested a much lower spatial resolution than expected. In this paper, we developed the SDI point-spread function (PSF) and Image Bivariate Optimization Algorithm (SPIBOA) to improve the quality of SDI images. The bivariate optimization method smartly combines deep learning with optical system modeling. Despite the lack of information about the real image taken by SDI and the optical system function, this algorithm effectively estimates the PSF of the SDI imaging system directly from a large sample of observational data. We use the estimated PSF to conduct deconvolution correction to observed SDI images, and the resulting images show that the spatial resolution after correction has increased by a factor of more than three with respect to the observed ones. Meanwhile, our method also significantly reduces the inherent noise in the observed SDI images. The SPIBOA has now been successfully integrated into the routine SDI data processing, providing important support for the scientific studies based on the data. The development and application of SPIBOA also pave new ways to identify astronomical telescope systems and enhance observational image quality. Some essential factors and precautions in applying the SPIBOA method are also discussed.

astro-ph.SR↗

arXiv2024

The Domain Wall Soliton's Tension

We calculate the one-loop tension of the domain wall soliton in the $ϕ^4$ double-well model. Our result agrees with previous results from Dashen, Hasslacher and Neveu (1974) in 1+1d and Jaimunga, Semenoff and Zarembo (1999) in 2+1d. After an additional 25 year interval, we have obtained a one-loop tension correction of $0.0410959m^3$ in 3+1d. In this case, unlike lower-dimensional cases, even after normal ordering there are ultraviolet divergences that require both mass and also coupling constant renormalization. We renormalized the coupling so that the three-point interaction in the effective potential is given by its tree level value at zero external momenta.

hep-th↗

arXiv2024

Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions

The rise of large language models (LLMs) offers new opportunities for automatic error detection in education, particularly for math word problems (MWPs). While prior studies demonstrate the promise of LLMs as error detectors, they overlook the presence of multiple valid solutions for a single MWP. Our preliminary analysis reveals a significant performance gap between conventional and alternative solutions in MWPs, a phenomenon we term conformity bias in this work. To mitigate this bias, we introduce the Ask-Before-Detect (AskBD) framework, which generates adaptive reference solutions using LLMs to enhance error detection. Experiments on 200 examples of GSM8K show that AskBD effectively mitigates bias and improves performance, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting.

cs.CL↗

arXiv2024

(Anti-)Stokes Scattering on the Domain Wall String

In a general (2+1)-dimensional scalar model, we consider the scattering of a single quantum of radiation off a domain wall string, which excites or de-excites the wall's internal shape mode. We refer to these two process as Stokes and anti-Stokes scattering. We calculate the probability densities for these processes to first order in quantum field theory, as a function of incoming momenta and angles. We include both the case in which the incident particle is transmitted and also that in which it bounces backward. Our results are given as finite-dimensional integrals of normal modes and elementary functions, and numerical results are presented in the particular case of the $ϕ^4$ double-well model.

hep-th↗

arXiv2024

A Survey of Calibration Process for Black-Box LLMs

Large Language Models (LLMs) demonstrate remarkable performance in semantic understanding and generation, yet accurately assessing their output reliability remains a significant challenge. While numerous studies have explored calibration techniques, they primarily focus on White-Box LLMs with accessible parameters. Black-Box LLMs, despite their superior performance, pose heightened requirements for calibration techniques due to their API-only interaction constraints. Although recent researches have achieved breakthroughs in black-box LLMs calibration, a systematic survey of these methodologies is still lacking. To bridge this gap, we presents the first comprehensive survey on calibration techniques for black-box LLMs. We first define the Calibration Process of LLMs as comprising two interrelated key steps: Confidence Estimation and Calibration. Second, we conduct a systematic review of applicable methods within black-box settings, and provide insights on the unique challenges and connections in implementing these key steps. Furthermore, we explore typical applications of Calibration Process in black-box LLMs and outline promising future research directions, providing new perspectives for enhancing reliability and human-machine alignment. This is our GitHub link: https://github.com/LiangruXie/Calibration-Process-in-Black-Box-LLMs

cs.AI↗

arXiv2024

Stochastic homogenization for two dimensional Navier--Stokes equations with random coefficients

This paper derives the stochastic homogenization for two dimensional Navier--Stokes equations with random coefficients. By means of weak convergence method and Stratonovich--Khasminskii averaging principle approach, the solution of two dimensional Navier--Stokes equations with random coefficients converges in distribution to the solution of two dimensional Navier--Stokes equations with constant coefficients.

math.AP↗

arXiv2024

Automated Detection of Inter-Language Design Smells in Multi-Language Deep Learning Frameworks

Nowadays, most DL frameworks (DLFs) use multilingual programming of Python and C/C++, facilitating the flexibility and performance of the DLF. However, inappropriate interlanguage interaction may introduce design smells involving multiple programming languages (PLs), i.e., Inter-Language Design Smells (ILDS). Despite the negative impact of ILDS on multi-language DLFs, there is a lack of an automated approach for detecting ILDS in multi-language DLFs and a comprehensive understanding on ILDS in such DLFs. This work automatically detects ILDS in multi-language DLFs written in the combination of Python and C/C++, and to obtain a understanding on such ILDS in DLFs. We first developed an approach to automatically detecting ILDS in the multi-language DLFs written in the combination of Python and C/C++, including a number of ILDS and their detection rules defined based on inter-language communication mechanisms and code analysis. We then developed the CPSMELL tool that implements detection rules for automatically detecting such ILDS, and manually validated the accuracy of the tool. Finally, we performed a study to evaluate the ILDS in multi-language DLFs. We proposed seven ILDS and achieved an accuracy of 98.17% in the manual validation of CPSMELL in 5 popular multi-language DLFs. The study results revealed that among the 5 DLFs, TensorFlow, PyTorch, and PaddlePaddle exhibit relatively high prevalence of ILDS; each smelly file contains around 5 ILDS instances on average, with ILDS Long Lambda Function For Inter-language Binding and Unused Native Entity being relatively prominent; throughout the evolution process of the 5 DLFs, some ILDS were resolved to a certain extent, but the overall count of ILDS instances shows an upward trend. The automated detection of the proposed ILDS achieved a high accuracy, and the study provides a comprehensive understanding on ILDS in the multi-language DLFs.

cs.SE↗

arXiv2024

Dynamic Prompt Allocation and Tuning for Continual Test-Time Adaptation

Continual test-time adaptation (CTTA) has recently emerged to adapt a pre-trained source model to continuously evolving target distributions, which accommodates the dynamic nature of real-world environments. To mitigate the risk of catastrophic forgetting in CTTA, existing methods typically incorporate explicit regularization terms to constrain the variation of model parameters. However, they cannot fundamentally resolve catastrophic forgetting because they rely on a single shared model to adapt across all target domains, which inevitably leads to severe inter-domain interference. In this paper, we introduce learnable domain-specific prompts that guide the model to adapt to corresponding target domains, thereby partially disentangling the parameter space of different domains. In the absence of domain identity for target samples, we propose a novel dynamic Prompt AllocatIon aNd Tuning (PAINT) method, which utilizes a query mechanism to dynamically determine whether the current samples come from a known domain or an unexplored one. For known domains, the corresponding domain-specific prompt is directly selected, while for previously unseen domains, a new prompt is allocated. Prompt tuning is subsequently performed using mutual information maximization along with structural regularization. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our PAINT method for CTTA. We have released our code at https://github.com/Cadezzyr/PAINT.

cs.LG↗

arXiv2024

Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning

In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels. The conventional PLL assumes the noisy labels are randomly generated (instance-independent), while in practical scenarios, the noisy labels are always instance-dependent and are highly related to the sample features, leading to the instance-dependent partial label learning (IDPLL) problem. Instance-dependent noisy label is a double-edged sword. On one side, it may promote model training as the noisy labels can depict the sample to some extent. On the other side, it brings high label ambiguity as the noisy labels are quite undistinguishable from the ground-truth label. To leverage the nuances of IDPLL effectively, for the first time we create class-wise embeddings for each sample, which allow us to explore the relationship of instance-dependent noisy labels, i.e., the class-wise embeddings in the candidate label set should have high similarity, while the class-wise embeddings between the candidate label set and the non-candidate label set should have high dissimilarity. Moreover, to reduce the high label ambiguity, we introduce the concept of class prototypes containing global feature information to disambiguate the candidate label set. Extensive experimental comparisons with twelve methods on six benchmark data sets, including four fine-grained data sets, demonstrate the effectiveness of the proposed method. The code implementation is publicly available at https://github.com/Yangfc-ML/CEL.

cs.LG↗