arXiv subjects

Jiacheng Huang

Publications and source records attributed to Jiacheng Huang.

18 recordsLinked to original sources

arXiv2026

From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning

Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning strategies and tool-use decisions across users. This setting raises key challenges: generic rewards cannot capture heterogeneous user preferences, observed behaviors are entangled with conformity effects, and flat memories cannot support personalized skill retrieval. To this end, we propose a unified personalized Agentic RL framework that embeds personalization into training-time optimization. At its core is \emph{Personalized Anchor Reward-Decoupled Policy Optimization} (\textbf{PARPO}), which decouples generic task-quality rewards from personalized preference rewards and uses user-specific anchors to stabilize learning under heterogeneous reward scales. We further introduce a two-stage preference-disentangled reward model and \emph{Preference-Aligned Skill Evolution Graph Memory} (\textbf{PSGM}) for personalized supervision and preference-aligned skill retrieval. Together, they form a closed loop of preference identification, policy optimization, and structured skill accumulation. Experiments on ETAPP, ETAPP-Hard, and SJAgent show that our framework consistently outperforms strong memory and RL baselines. Code and data are included in the supplementary materials.

cs.CL↗

arXiv2025

EMODIS: A Benchmark for Context-Dependent Emoji Disambiguation in Large Language Models

Large language models (LLMs) are increasingly deployed in real-world communication settings, yet their ability to resolve context-dependent ambiguity remains underexplored. In this work, we present EMODIS, a new benchmark for evaluating LLMs' capacity to interpret ambiguous emoji expressions under minimal but contrastive textual contexts. Each instance in EMODIS comprises an ambiguous sentence containing an emoji, two distinct disambiguating contexts that lead to divergent interpretations, and a specific question that requires contextual reasoning. We evaluate both open-source and API-based LLMs, and find that even the strongest models frequently fail to distinguish meanings when only subtle contextual cues are present. Further analysis reveals systematic biases toward dominant interpretations and limited sensitivity to pragmatic contrast. EMODIS provides a rigorous testbed for assessing contextual disambiguation, and highlights the gap in semantic reasoning between humans and LLMs.

cs.CL↗

arXiv2025

NineToothed: A Triton-Based High-Level Domain-Specific Language for Machine Learning

The emergence of deep learning domain-specific languages (DSLs) has substantially reduced the obstacles in developing high-performance, cross-platform compute kernels. However, current DSLs, such as Triton, still demand that developers possess expertise in parallel programming and expose them to many low-level details. This requirement complicates the development process and adds to the difficulty of maintaining compute kernels. Consequently, developing a new programming model that supports serial programming for deep learning workloads is crucial. This paper introduces NineToothed, a domain-specific language that offers serial semantics for machine learning programming. Through the automatic transformation of serial code into parallel code, NineToothed significantly streamlines the development process while causing minimal performance degradation. NineToothed encompasses (1) a language with tensor-oriented metaprogramming (TOM) that adopts the arrange-and-apply paradigm, enabling the expression of tiled computations without the need to manage low-level details and (2) a code generator for generating high-performance parallel code. Our evaluation results indicate that NineToothed can greatly simplify compute kernel development while maintaining performance comparable to that of Triton.

cs.DC↗

arXiv2025

TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators

Triton, a high-level Python-like language designed for building efficient GPU kernels, is widely adopted in deep learning frameworks due to its portability, flexibility, and accessibility. However, programming and parallel optimization still require considerable trial and error from Triton developers. Despite advances in large language models (LLMs) for conventional code generation, these models struggle to generate accurate, performance-optimized Triton code, as they lack awareness of its specifications and the complexities of GPU programming. More critically, there is an urgent need for systematic evaluations tailored to Triton. In this work, we introduce TritonBench, the first comprehensive benchmark for Triton operator generation. TritonBench features two evaluation channels: a curated set of 184 real-world operators from GitHub and a collection of operators aligned with PyTorch interfaces. Unlike conventional code benchmarks prioritizing functional correctness, TritonBench also profiles efficiency performance on widely deployed GPUs aligned with industry applications. Our study reveals that current state-of-the-art code LLMs struggle to generate efficient Triton operators, highlighting a significant gap in high-performance code generation. TritonBench will be available at https://github.com/thunlp/TritonBench.

cs.CL↗

arXiv2024

Will you donate money to a chatbot? The effect of chatbot anthropomorphic features and persuasion strategies on willingness to donate

This work investigates the causal mechanism behind the effect of chatbot personification and persuasion strategies on users' perceptions and donation likelihood. In a 2 (personified vs. non-personified chatbot) x 2 (emotional vs. logical persuasion strategy) between-subjects experiment (N=76), participants engaged with a chatbot that represented a non-profit charitable organization. The results suggest that interaction with a personified chatbot evokes perceived anthropomorphism; however, it does not elicit greater willingness to donate. In fact, we found that commonly used anthropomorphic features, like name and narrative, led to negative attitudes toward an AI agent in the donation context. Our results showcase a preference for non-personified chatbots paired with logical persuasion appeal, emphasizing the significance of consistency in chatbot interaction, mirroring human-human engagement. We discuss the importance of moving from exploring the common scenario of a chatbot with machine identity vs. a chatbot with human identity in light of the recent regulations of AI systems.

cs.HC↗

arXiv2024

Chain Association-based Attacking and Shielding Natural Language Processing Systems

Association as a gift enables people do not have to mention something in completely straightforward words and allows others to understand what they intend to refer to. In this paper, we propose a chain association-based adversarial attack against natural language processing systems, utilizing the comprehension gap between humans and machines. We first generate a chain association graph for Chinese characters based on the association paradigm for building search space of potential adversarial examples. Then, we introduce an discrete particle swarm optimization algorithm to search for the optimal adversarial examples. We conduct comprehensive experiments and show that advanced natural language processing models and applications, including large language models, are vulnerable to our attack, while humans appear good at understanding the perturbed text. We also explore two methods, including adversarial training and associative graph-based recovery, to shield systems from chain association-based attack. Since a few examples that use some derogatory terms, this paper contains materials that may be offensive or upsetting to some people.

cs.CL↗

arXiv2024

IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems

Adversarial examples, which are inputs deliberately perturbed with imperceptible changes to induce model errors, have raised serious concerns for the reliability and security of deep neural networks (DNNs). While adversarial attacks have been extensively studied in continuous data domains such as images, the discrete nature of text presents unique challenges. In this paper, we propose Irony-based Adversarial Examples (IAE), a method that transforms straightforward sentences into ironic ones to create adversarial text. This approach exploits the rhetorical device of irony, where the intended meaning is opposite to the literal interpretation, requiring a deeper understanding of context to detect. The IAE method is particularly challenging due to the need to accurately locate evaluation words, substitute them with appropriate collocations, and expand the text with suitable ironic elements while maintaining semantic coherence. Our research makes the following key contributions: (1) We introduce IAE, a strategy for generating textual adversarial examples using irony. This method does not rely on pre-existing irony corpora, making it a versatile tool for creating adversarial text in various NLP tasks. (2) We demonstrate that the performance of several state-of-the-art deep learning models on sentiment analysis tasks significantly deteriorates when subjected to IAE attacks. This finding underscores the susceptibility of current NLP systems to adversarial manipulation through irony. (3) We compare the impact of IAE on human judgment versus NLP systems, revealing that humans are less susceptible to the effects of irony in text.

cs.CL↗

arXiv2023

Efficient spectral broadening and few-cycle pulse generation with multiple thin water films

High-energy, few-cycle laser pulses are essential for numerous applications in the fields of ultrafast optics and strong-field physics, due to their ultrafast temporal resolution and high peak intensity. In this work, different from the traditional hollow-core fibers and multiple thin solid plates, we represent the first demonstration of the octave-spanning supercontinuum broadening by utilizing multiple ultrathin liquid films (MTLFs) as the nonlinear media. The continuum covers a range from 380 to 1050 nm, corresponding to a Fourier transform limit pulse width of 2.5 fs, when 35 fs Ti:sapphire laser pulse is applied on the MTLFs. The output pulses are compressed to 3.9 fs by employing chirped mirrors. Furthermore, a continuous high-order harmonic spectrum up to the 33rd order is realized by subjecting the compressed laser pulses to interact with Kr gas. The utilization of flowing water films eliminates permanent optical damage and enables wider and stronger spectrum broadening. Therefore, this MTLFs scheme provides new solutions for the generation of highly efficient femtosecond supercontinuum and nonlinear pulse compression, with potential applications in the fields of strong-field physics and attosecond science.

physics.optics↗

arXiv2023

Deep Active Alignment of Knowledge Graph Entities and Schemata

Knowledge graphs (KGs) store rich facts about the real world. In this paper, we study KG alignment, which aims to find alignment between not only entities but also relations and classes in different KGs. Alignment at the entity level can cross-fertilize alignment at the schema level. We propose a new KG alignment approach, called DAAKG, based on deep learning and active learning. With deep learning, it learns the embeddings of entities, relations and classes, and jointly aligns them in a semi-supervised manner. With active learning, it estimates how likely an entity, relation or class pair can be inferred, and selects the best batch for human labeling. We design two approximation algorithms for efficient solution to batch selection. Our experiments on benchmark datasets show the superior accuracy and generalization of DAAKG and validate the effectiveness of all its modules.

cs.DB↗

arXiv2023

What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings

Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experimental evidence to support our theoretical analysis. We propose two simple but effective methods inspired by the fixpoint computation in similarity flooding, and demonstrate their effectiveness on benchmark datasets. Our work bridges the gap between recent embedding-based models and the conventional similarity flooding algorithm. It would improve our understanding of and increase our faith in embedding-based EA.

cs.LG↗

arXiv2023

Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs

In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information to improve KG embeddings and downstream tasks. We pre-train a large teacher KG embedding model over linked multi-source KGs and distill knowledge to train a student model for a task-specific KG. To enable knowledge transfer across different KGs, we use entity alignment to build a linked subgraph for connecting the pre-trained KGs and the target KG. The linked subgraph is re-trained for three-level knowledge distillation from the teacher to the student, i.e., feature knowledge distillation, network knowledge distillation, and prediction knowledge distillation, to generate more expressive embeddings. The teacher model can be reused for different target KGs and tasks without having to train from scratch. We conduct extensive experiments to demonstrate the effectiveness and efficiency of our framework.

cs.CL↗

arXiv2022

Cost-effective BlackWater Raft on Highly Unreliable Nodes at Scale Out

The Raft algorithm maintains strong consistency across data replicas in Cloud. This algorithm divides nodes into leaders and followers, to satisfy read/write requests spanning geo-diverse sites. With the increase of workload, Raft shall provide scale-out performance in proportion. However, traditional scale-out techniques encounter bottlenecks in Raft, and when the provisioned sites exhaust local resources, the performance loss will grow exponentially. To provide scalability in Raft, this paper proposes a cost-effective mechanism for elastic auto-scaling in Raft, called BlackWater-Raft or BW-Raft. BW-Raft extends the original Raft with the following abstractions: (1) secretary nodes that take over expensive log synchronization operations from the leader, relaxing the performance constraints on locks. (2) massive low cost observer nodes that handle reads only, improving throughput for typical data intensive services. These abstractions are stateless, allowing elastic scale-out on unreliable yet cheap spot instances. In theory, we demonstrate that BW-Raft can maintain Raft's strong consistency guarantees when scaling out, processing a 50X increase in the number of nodes compared to the original Raft. We have prototyped the BW-Raft on key-value services and evaluated it with many state-of-the-arts on Amazon EC2 and Alibaba Cloud. Our results show that within the same budget, BW-Raft's resource footprint increments are 5-7X smaller than Multi-Raft, and 2X better than original Raft. Using spot instances, BW-Raft can reduces costs by 84.5\% compared to Multi-Raft. In the real world experiments, BW-Raft improves goodput of the 95th-percentile SLO by 9.4X, thus serving as an alternative for services scaling out with strong consistency.

cs.DC↗

arXiv2022

Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data

Knowledge graphs (KGs) have become a valuable asset for many AI applications. Although some KGs contain plenty of facts, they are widely acknowledged as incomplete. To address this issue, many KG completion methods are proposed. Among them, open KG completion methods leverage the Web to find missing facts. However, noisy data collected from diverse sources may damage the completion accuracy. In this paper, we propose a new trustworthy method that exploits facts for a KG based on multi-sourced noisy data and existing facts in the KG. Specifically, we introduce a graph neural network with a holistic scoring function to judge the plausibility of facts with various value types. We design value alignment networks to resolve the heterogeneity between values and map them to entities even outside the KG. Furthermore, we present a truth inference model that incorporates data source qualities into the fact scoring function, and design a semi-supervised learning way to infer the truths from heterogeneous values. We conduct extensive experiments to compare our method with the state-of-the-arts. The results show that our method achieves superior accuracy not only in completing missing facts but also in discovering new facts.

cs.IR↗

arXiv2021

Data Augmentation for Text Generation Without Any Augmented Data

Data augmentation is an effective way to improve the performance of many neural text generation models. However, current data augmentation methods need to define or choose proper data mapping functions that map the original samples into the augmented samples. In this work, we derive an objective to formulate the problem of data augmentation on text generation tasks without any use of augmented data constructed by specific mapping functions. Our proposed objective can be efficiently optimized and applied to popular loss functions on text generation tasks with a convergence rate guarantee. Experiments on five datasets of two text generation tasks show that our approach can approximate or even surpass popular data augmentation methods.

cs.CL↗

arXiv2020

Rule-Guided Graph Neural Networks for Recommender Systems

To alleviate the cold start problem caused by collaborative filtering in recommender systems, knowledge graphs (KGs) are increasingly employed by many methods as auxiliary resources. However, existing work incorporated with KGs cannot capture the explicit long-range semantics between users and items meanwhile consider various connectivity between items. In this paper, we propose RGRec, which combines rule learning and graph neural networks (GNNs) for recommendation. RGRec first maps items to corresponding entities in KGs and adds users as new entities. Then, it automatically learns rules to model the explicit long-range semantics, and captures the connectivity between entities by aggregation to better encode various information. We show the effectiveness of RGRec on three real-world datasets. Particularly, the combination of rule learning and GNNs achieves substantial improvement compared to methods only using either of them.

cs.LG↗

arXiv2020

TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs

Learning knowledge graph (KG) embeddings has received increasing attention in recent years. Most embedding models in literature interpret relations as linear or bilinear mapping functions to operate on entity embeddings. However, we find that such relation-level modeling cannot capture the diverse relational structures of KGs well. In this paper, we propose a novel edge-centric embedding model TransEdge, which contextualizes relation representations in terms of specific head-tail entity pairs. We refer to such contextualized representations of a relation as edge embeddings and interpret them as translations between entity embeddings. TransEdge achieves promising performance on different prediction tasks. Our experiments on benchmark datasets indicate that it obtains the state-of-the-art results on embedding-based entity alignment. We also show that TransEdge is complementary with conventional entity alignment methods. Moreover, it shows very competitive performance on link prediction.

cs.AI↗

arXiv2020

Crowdsourced Collective Entity Resolution with Relational Match Propagation

Knowledge bases (KBs) store rich yet heterogeneous entities and facts. Entity resolution (ER) aims to identify entities in KBs which refer to the same real-world object. Recent studies have shown significant benefits of involving humans in the loop of ER. They often resolve entities with pairwise similarity measures over attribute values and resort to the crowds to label uncertain ones. However, existing methods still suffer from high labor costs and insufficient labeling to some extent. In this paper, we propose a novel approach called crowdsourced collective ER, which leverages the relationships between entities to infer matches jointly rather than independently. Specifically, it iteratively asks human workers to label picked entity pairs and propagates the labeling information to their neighbors in distance. During this process, we address the problems of candidate entity pruning, probabilistic propagation, optimal question selection and error-tolerant truth inference. Our experiments on real-world datasets demonstrate that, compared with state-of-the-art methods, our approach achieves superior accuracy with much less labeling.

cs.DB↗

arXiv2020

Open Knowledge Enrichment for Long-tail Entities

Knowledge bases (KBs) have gradually become a valuable asset for many AI applications. While many current KBs are quite large, they are widely acknowledged as incomplete, especially lacking facts of long-tail entities, e.g., less famous persons. Existing approaches enrich KBs mainly on completing missing links or filling missing values. However, they only tackle a part of the enrichment problem and lack specific considerations regarding long-tail entities. In this paper, we propose a full-fledged approach to knowledge enrichment, which predicts missing properties and infers true facts of long-tail entities from the open Web. Prior knowledge from popular entities is leveraged to improve every enrichment step. Our experiments on the synthetic and real-world datasets and comparison with related work demonstrate the feasibility and superiority of the approach.

cs.IR↗