Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment
sigir26-212 · Full research paper · Yiran Qiao, Xiang Ao, Jing Chen, Yang Liu, Qiwei Zhong, Qing He
RAG for Domain Applications · 50% Multimodal Fake News Detection · 50%
Abstract
The rise of live streaming has transformed online interaction, enabling massive real-time engagement but also exposing platforms to complex risks such as scams and coordinated malicious behaviors. Detecting these risks is challenging because harmful actions often accumulate gradually and recur across seemingly unrelated streams. To address this, we propose CS-VAR (Cross-Session Evidence-Aware Retrieval-Augmented Detector) for live streaming risk assessment. In CS-VAR, a lightweight, domain-specific model performs fast session-level risk inference, guided during training by a Large Language Model (LLM) that reasons over retrieved cross-session behavioral evidence and transfers its local-to-global insights to the small model. This design enables the small model to recognize recurring patterns across streams, perform structured risk assessment, and maintain efficiency for real-time deployment. Extensive offline experiments on large-scale industrial datasets, combined with online validation, demonstrate the state-of-the-art performance of CS-VAR. Furthermore, CS-VAR provides interpretable, localized signals that effectively empower real-world moderation for live streaming.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Zhi Zeng 0001 | 61 | 58 From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild (2026) Multimodal Fake News Detection 58 Event-Radar: Event-driven Multi-View Learning for Multimodal Fake News Detection (2024) Multimodal Fake News Detection 58 Understand, Refine and Summarize: Multi-View Knowledge Progressive Enhancement Learning for Fake News Video Detection (2025) Multimodal Fake News Detection |
|
| 2 | Zihan Ma 0001 | 61 | 59 How Do Social Bots Participate in Misinformation Spread? A Comprehensive Dataset and Analysis (2025) Social Media and User Modelling 58 From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild (2026) Multimodal Fake News Detection 58 Event-Radar: Event-driven Multi-View Learning for Multimodal Fake News Detection (2024) Multimodal Fake News Detection |
|
| 3 | Bo Wang 0069 | 59 | 65 Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection (2020) Graph Learning for Text-Attributed and Heterogeneous Networks 58 GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse (2026) Multimodal Fake News Detection 58 ExplainHM++: Explainable Harmful Meme Detection With Retrieval-Augmented Debate Between Large Multimodal Models (2026) Multimodal Fake News Detection |
Area chair
| Area chair | Match | |
|---|---|---|
| Yi R. Fung 0001 | 40 |
Area-chair candidates (6)
| Yi R. Fung 0001 assigned | 40 | 10 papers | |
| Hongjin Qian | 32 | 12 papers | |
| Xiaoxi Li 0005 | 32 | 15 papers | |
| Kam-Fai Wong | 31 | 6 papers | |
| Xiaoye Qu | 31 | 15 papers | |
| Jun Xu 0001 | 29 | 2 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Ruichao Yang | 68 | 3 | 66 A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM (2026) RAG for Domain Applications 64 GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse (2026) Multimodal Fake News Detection |
|
| 2 | Zhi Zeng 0001 assigned | 61 | 3 | 58 From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild (2026) Multimodal Fake News Detection 58 Event-Radar: Event-driven Multi-View Learning for Multimodal Fake News Detection (2024) Multimodal Fake News Detection |
|
| 3 | Zihan Ma 0001 assigned | 61 | 3 | 59 How Do Social Bots Participate in Misinformation Spread? A Comprehensive Dataset and Analysis (2025) Social Media and User Modelling 58 From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild (2026) Multimodal Fake News Detection |
|
| 4 | Jian Lang | 60 | 3 | 58 Enhancing fake news video detection with self-driven question-answer from LMMs (2026) Multimodal Fake News Detection 58 Biting Off More Than You Can Detect: Retrieval-Augmented Multimodal Experts for Short Video Hate Detection (2025) Multimodal Fake News Detection |
|
| 5 | Bo Wang 0069 assigned | 59 | 3 | 65 Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection (2020) Graph Learning for Text-Attributed and Heterogeneous Networks 58 GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse (2026) Multimodal Fake News Detection |
|
| 6 | Huaiwen Zhang | 52 | 3 | 58 Cross-domain Rumor Detection via Test-Time Adaptation and Large Language Models (2025) Multimodal Fake News Detection 58 T3RD: Test-Time Training for Rumor Detection on Social Media (2024) Multimodal Fake News Detection |
|
| 7 | Mariano Barone | 48 | 3 | 66 Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verification (2025) RAG for Domain Applications 64 SynthMed: Generating and Detecting Multimodal Deepfakes for Healthcare Communication (2025) Multimodal Fake News Detection |
|
| 9 | Yu-An Liu 0028 | 34 | 3 | 35 On the Robustness of Generative Information Retrieval Models: An Out-of-Distribution Perspective (2025) Generative Retrieval 33 Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models (2025) Robustness and Adversarial IR |
|
| 10 | Ruqing Zhang 0001 | 34 | 3 | 61 CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks (2026) Generative Retrieval 35 Boosting Retrieval-Augmented Generation with Generation-Augmented Retrieval: A Co-Training Approach (2025) Generative Retrieval |
|
| 11 | Weizhi Xu 0002 | 33 | 3 | 34 Bias Mitigation for Evidence-aware Fake News Detection by Causal Intervention (2022) Automated Fact Checking and Claim Verification 34 Adversarial Contrastive Learning for Evidence-Aware Fake News Detection With Graph Neural Networks (2024) Automated Fact Checking and Claim Verification |
|
| 12 | Jing Liu 0022 | 32 | 3 | 35 Competition-based user expertise score estimation (2011) Social Media and User Modelling 35 Question Difficulty Estimation in Community Question Answering Services (2013) Social Media and User Modelling |
|
| 13 | Xingyu Tan 0001 | 32 | 3 | 35 PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation (2026) Multimodal and Graph RAG 34 MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning (2026) KG-Augmented LLM Reasoning |
|
| 14 | Chen Zhao 0013 | 32 | 3 | 34 FinDVer: Explainable Claim Verification over Long and Hybrid-content Financial Documents (2024) Automated Fact Checking and Claim Verification 34 Large Language Models Help Humans Verify Truthfulness - Except When They Are Convincingly Wrong (2024) Automated Fact Checking and Claim Verification |
|
| 15 | Farima Fatahi Bayat | 32 | 3 | 34 FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation (2025) Automated Fact Checking and Claim Verification 34 Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding (2024) Automated Fact Checking and Claim Verification |
|
| 18 | Di Wu 0054 | 32 | 3 | 56 Repoformer: Selective Retrieval for Repository-Level Code Completion (2024) Efficient and Long-Context RAG 37 LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (2025) Conversational Search and Retrieval |
|
| 19 | Shu Zhou 0002 | 32 | 3 | 46 When MLLMs Meet ICH: A visual retrieval-augmented generation-based method for intangible cultural heritage image recognition-take Shadow Puppetry as a case (2026) Universal Multimodal Embedding and MLLM Retrieval 38 Cascaded Verification Framework: A Progressive Approach for Mitigating Hallucinations in Large Language Models (2026) Knowledge Conflict and Faithfulness |
|
| 20 | Idan Szpektor | 31 | 3 | 37 On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method (2023) Conversational Search and Retrieval 34 TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models (2023) Automated Fact Checking and Claim Verification |
|
| 22 | Yujia Zhou 0002 | 31 | 3 | 35 Grounding Language Model with Chunking-Free In-Context Retrieval (2024) Generative Retrieval 35 CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks (2024) Generative Retrieval |
|
| 23 | Armin Toroghi | 31 | 3 | 37 CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge (2025) Automated Fact Checking and Claim Verification 37 Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering (2024) Automated Fact Checking and Claim Verification |
|
| 25 | Xinyu Ma 0001 | 31 | 3 | 38 Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation (2025) LLM-Derived Knowledge Infusion 31 Model Editing for New Document Integration in Generative Information Retrieval (2026) Generative Retrieval |
|
| 26 | Qinggang Zhang | 30 | 3 | 36 Facilitating Generative Retrieval with Logical Denoising for Interpretable Conversational Search (2026) Personalized and Conversational RAG 35 KnowGPT: Knowledge Graph based Prompting for Large Language Models (2024) Multimodal and Graph RAG |
|
| 27 | Qingyi Si | 30 | 3 | 37 Are Large Language Models Table-based Fact-Checkers? (2024) Automated Fact Checking and Claim Verification 33 Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering (2025) Universal Multimodal Embedding and MLLM Retrieval |
|
| 28 | Farzad Shami | 30 | 3 | 31 From Single to Multi-agent Reasoning: Advancing GeneGPT for Genomics QA (2026) Retrieval-Augmented and Open-Domain QA 29 Fact Verification in Knowledge Graphs Using LLMs (2025) KG-Augmented LLM Reasoning |
|
| 29 | Jialong Wu 0007 | 30 | 3 | 32 AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation (2025) Query Reformulation and Expansion 32 AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2025) Query Reformulation and Expansion |
|
| 30 | Weiwei Sun 0001 | 30 | 3 | 32 TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy (2025) Reasoning-Intensive Retrieval and Ranking 32 DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation (2020) Conversational Search and Retrieval |
|
| 31 | Wenyu Huang | 30 | 3 | 31 Prompting large language models with knowledge graphs for question answering involving long-tail facts (2025) KG-Augmented LLM Reasoning 30 Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation (2025) Multi-hop and Complex Reasoning QA |
|
| 32 | Qisheng Hu | 30 | 3 | 34 Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance? (2025) Automated Fact Checking and Claim Verification 33 Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification (2026) Automated Fact Checking and Claim Verification |
|
| 33 | Tingyu Song | 30 | 3 | 34 LimRank: Less is More for Reasoning-Intensive Information Reranking (2025) Evidence Selection and Context Refinement 30 Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems (2026) Reasoning-Intensive Retrieval and Ranking |
|
| 34 | Jinheon Baek | 30 | 3 | 44 Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks (2023) Retrieval-Augmented and Open-Domain QA 37 Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement (2023) Conversational Search and Retrieval |
|
| 35 | Jimeng Sun 0001 | 30 | 3 | 46 A Survey on Unifying Large Language Models and Knowledge Graphs for Biomedicine and Healthcare (2025) KG-Augmented LLM Reasoning 44 Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (2025) Multimodal and Graph RAG |