Litian Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Litian Zhang has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Chaozhuo Li
Microsoft Research Asia, Beijing, China
5 shared publications - Feiran Huang
Beihang University
5 shared publications - Xiaoming Zhang
Beihang University, Beijing, China
5 shared publications - Philip S. Yu
University of Illinois Chicago
4 shared publications - Xi Zhang
Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications, Beijing, China
4 shared publications Chaozhuo Li
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16151-16159
Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16151-16159
Open AccessReasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19744-19762
mmWave Radar-Based Unsupervised Person ReID via Multi-Level Mutual Signal Contrastive Learning
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19744-19762
mmWave Radar-Based Unsupervised Person ReID via Multi-Level Mutual Signal Contrastive Learning
- Open Access
- 2 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (6) , 1-41
Decomposition, Think and Action: Alleviating Hallucinations of Large Language Models with Reasoning–Evidence Interactive Augmented Graph
Hallucination remains a major obstacle to the domain generalizability and reliability of Large Language Models (LLMs). Recent approaches address this issue by integrating Retrieval-Augmented Generation (RAG) with stepwise reasoning processes to iteratively retrieve knowledge. However, indiscriminate incorporation of external knowledge may interfere with reasoning, increasing latency and amplifying error accumulation. Moreover, existing methods rely on a unidirectional flow of external knowledge into LLMs while neglecting internal–external knowledge synergy, limiting autonomous reasoning capability. To address these limitations, we propose the Reasoning–Evidence Interactive Augmented Graph (RE-IAG), a framework that couples reasoning with evidence through a staged triggering mechanism and structured interaction. RE-IAG performs localized refinement of intermediate reasoning via adaptive branching under uncertainty and selectively triggers retrieval when internal reasoning stagnates. Crucially, it organizes both internal reasoning and retrieved evidence into aligned graph structures, enabling structure-guided verification and fine-grained refinement of intermediate conclusions. This design transforms retrieval from passive augmentation into an active constraint on reasoning, reducing error propagation, alleviating knowledge conflicts, and improving knowledge integration for hallucination mitigation. Extensive experiments on four multi-hop QA benchmarks show that RE-IAG outperforms adaptive RAG baselines, achieves competitive or superior performance to RL-based approaches, and demonstrates strong robustness and generalization across model scales and architectures.
- 2 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (6) , 1-41
Open AccessDecomposition, Think and Action: Alleviating Hallucinations of Large Language Models with Reasoning–Evidence Interactive Augmented Graph
Hallucination remains a major obstacle to the domain generalizability and reliability of Large Language Models (LLMs). Recent approaches address this issue by integrating Retrieval-Augmented Generation (RAG) with stepwise reasoning processes to iteratively retrieve knowledge. However, indiscriminate incorporation of external knowledge may interfere with reasoning, increasing latency and amplifying error accumulation. Moreover, existing methods rely on a unidirectional flow of external knowledge into LLMs while neglecting internal–external knowledge synergy, limiting autonomous reasoning capability. To address these limitations, we propose the Reasoning–Evidence Interactive Augmented Graph (RE-IAG), a framework that couples reasoning with evidence through a staged triggering mechanism and structured interaction. RE-IAG performs localized refinement of intermediate reasoning via adaptive branching under uncertainty and selectively triggers retrieval when internal reasoning stagnates. Crucially, it organizes both internal reasoning and retrieved evidence into aligned graph structures, enabling structure-guided verification and fine-grained refinement of intermediate conclusions. This design transforms retrieval from passive augmentation into an active constraint on reasoning, reducing error propagation, alleviating knowledge conflicts, and improving knowledge integration for hallucination mitigation. Extensive experiments on four multi-hop QA benchmarks show that RE-IAG outperforms adaptive RAG baselines, achieves competitive or superior performance to RL-based approaches, and demonstrates strong robustness and generalization across model scales and architectures.
- Top Cited Papers
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP, 1-32
Loki’s Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
Edgar Allan Poe noted, “Truth often lurks in the shadow of error,” highlighting the deep complexity intrinsic to the interplay between truth and falsehood, notably under conditions of cognitive and informational asymmetry. This dynamic is strikingly evident in large language models (LLMs). Despite their impressive linguistic generation capabilities, LLMs sometimes produce information that appears factually accurate but is, in reality, fabricated, an issue often referred to as “hallucinations.” The prevalence of these hallucinations can mislead users, affecting their judgments and decisions. In sectors such as finance, law, and healthcare, such misinformation risks causing substantial economic losses, legal disputes, and health risks, with wide-ranging consequences. In our research, we have methodically categorized and analyzed the causes, detection methods, and solutions related to LLM hallucinations. Our efforts specifically focus on elucidating the root causes of hallucinations and evaluating current strategies, thereby laying the groundwork for developing robust mitigation techniques.
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP, 1-32
Top Cited PapersLoki’s Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
Edgar Allan Poe noted, “Truth often lurks in the shadow of error,” highlighting the deep complexity intrinsic to the interplay between truth and falsehood, notably under conditions of cognitive and informational asymmetry. This dynamic is strikingly evident in large language models (LLMs). Despite their impressive linguistic generation capabilities, LLMs sometimes produce information that appears factually accurate but is, in reality, fabricated, an issue often referred to as “hallucinations.” The prevalence of these hallucinations can mislead users, affecting their judgments and decisions. In sectors such as finance, law, and healthcare, such misinformation risks causing substantial economic losses, legal disputes, and health risks, with wide-ranging consequences. In our research, we have methodically categorized and analyzed the causes, detection methods, and solutions related to LLM hallucinations. Our efforts specifically focus on elucidating the root causes of hallucinations and evaluating current strategies, thereby laying the groundwork for developing robust mitigation techniques.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1892-1902
LLMCBR: Large Language Model-based Multi-View and Multi-Grained Learning for Bundle Recommendation
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1892-1902
Open AccessLLMCBR: Large Language Model-based Multi-View and Multi-Grained Learning for Bundle Recommendation
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2127-2136
Reverse Chain-of-Thought and Causal Path Verification: A Modular Plugin for Aligning LLMs with Knowledge Graphs
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2127-2136
Open AccessReverse Chain-of-Thought and Causal Path Verification: A Modular Plugin for Aligning LLMs with Knowledge Graphs
- 19 August 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 184
Contrastive learning with hard negatives for sentence embeddings
- 19 August 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 184
Contrastive learning with hard negatives for sentence embeddings
- 23 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 294
Beyond entity alignment: Towards complete knowledge graph alignment via entity-relation synergy
- 23 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 294
Beyond entity alignment: Towards complete knowledge graph alignment via entity-relation synergy
- 4 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (4) , 2310-2325
Privacy-Preserving Image Retrieval in Cloud Computing via Adaptive Secret Keys and Self-Supervised Block-Augmented Pretraining
Privacy-Preserving Image Retrieval (PPIR) enables searching for similar images on cloud servers while safeguarding image privacy. PPIR uploads encrypted images to servers to address privacy concerns and then employs deep neural networks for retrieval on extracted features from cipher-images. However, current PPIR encrypts all images with the same secret keys to maintain consistent feature spaces, lacking support for adaptive keys where distinct images are encrypted with various keys. To this end, we propose a new PPIR scheme to support adaptive keys while keeping stable feature spaces. Specifically, we design ingenious image encryption to align with feature extraction during the JPEG compression process, incorporating encryptable orthogonal transformations, shuffling, stream cipher, and sign encryption operations. Our approach extracts well-designed absolute value sequences of local blocks and global histogram features from cipher-images, ensuring stable feature spaces under adaptive keys. To enhance model generalization performance, we employ Self-Supervised Contrastive Learning (SSCL) to build a pretraining model and propose a straightforward yet efficient block-sampling augmentation technique for the structured features to drive SSCL. Moreover, our retrieval model implements a dual-attention structure to capture dependencies among local block sequences and import scores of global features. Extensive experiments on four datasets demonstrate that our approach achieves superior retrieval accuracy compared to existing schemes and maintains excellent retrieval performance under adaptive keys, effectively preserving image privacy.
- 4 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (4) , 2310-2325
Privacy-Preserving Image Retrieval in Cloud Computing via Adaptive Secret Keys and Self-Supervised Block-Augmented Pretraining
Privacy-Preserving Image Retrieval (PPIR) enables searching for similar images on cloud servers while safeguarding image privacy. PPIR uploads encrypted images to servers to address privacy concerns and then employs deep neural networks for retrieval on extracted features from cipher-images. However, current PPIR encrypts all images with the same secret keys to maintain consistent feature spaces, lacking support for adaptive keys where distinct images are encrypted with various keys. To this end, we propose a new PPIR scheme to support adaptive keys while keeping stable feature spaces. Specifically, we design ingenious image encryption to align with feature extraction during the JPEG compression process, incorporating encryptable orthogonal transformations, shuffling, stream cipher, and sign encryption operations. Our approach extracts well-designed absolute value sequences of local blocks and global histogram features from cipher-images, ensuring stable feature spaces under adaptive keys. To enhance model generalization performance, we employ Self-Supervised Contrastive Learning (SSCL) to build a pretraining model and propose a straightforward yet efficient block-sampling augmentation technique for the structured features to drive SSCL. Moreover, our retrieval model implements a dual-attention structure to capture dependencies among local block sequences and import scores of global features. Extensive experiments on four datasets demonstrate that our approach achieves superior retrieval accuracy compared to existing schemes and maintains excellent retrieval performance under adaptive keys, effectively preserving image privacy.
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2278-2287
ModalSync: Synchronizing User Behavior with Multimodal Features for Multimodal Pre-training Recommendation
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2278-2287
Open AccessModalSync: Synchronizing User Behavior with Multimodal Features for Multimodal Pre-training Recommendation