PPaperPicks

Songlin Hu

Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China

38 papers at tracked venues · 25 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-7170-3809 ↗Homepage ↗

Venues

ACL ×12EMNLP ×8AAAI ×6NAACL ×3ACM MM ×2SIGIR ×2ECAI ×1ECML-PKDD ×1ICLR ×1ICML ×1NeurIPS ×1

Frequent coauthors

Dou Hu
DBLP profile ↗ORCID search ↗
×5
Mengyang Chen
DBLP profile ↗ORCID search ↗
×3
Zhenpeng Su
DBLP profile ↗ORCID search ↗
×3
Chaochen Gao
DBLP profile ↗ORCID search ↗
×3
Xikang Yang
DBLP profile ↗ORCID search ↗
×2
Peng Wang
DBLP profile ↗ORCID search ↗
×2
Guan Wang
DBLP profile ↗ORCID search ↗
×2
Boyu Qiao
DBLP profile ↗ORCID search ↗
×2
Chengwei Dai
DBLP profile ↗ORCID search ↗
×2
Guangyuan Ma
DBLP profile ↗ORCID search ↗
×2
Bingkang Shi
DBLP profile ↗ORCID search ↗
×1
Yiting Shen
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
    AAAI 2026 ·
    Xikang Yang
    DBLP profile ↗ORCID search ↗
  2. FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
    ACL 2026 ·
    Peng Wang
    DBLP profile ↗ORCID search ↗
  3. FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs
    ACL 2026 ·
    Bingkang Shi
    DBLP profile ↗ORCID search ↗
  4. Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents
    ACL 2026 ·
    Yiting Shen
    DBLP profile ↗ORCID search ↗
  5. Mitigating Adversarial Attacks by Transferring LLM-generated Narrative Reasoning for Robust Fake News Detection
    SIGIR 2026 ·
    Mengyang Chen
    DBLP profile ↗ORCID search ↗
  6. More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters
    ACL 2026 ·
    Guan Wang
    DBLP profile ↗ORCID search ↗
  7. Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective
    ACL 2026 ·
    Dou Hu
    DBLP profile ↗ORCID search ↗
  8. Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment
    ACL 2026 ·
    Guan Wang
    DBLP profile ↗ORCID search ↗
  9. An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding
    AAAI 2025 ·
    Dou Hu
    DBLP profile ↗ORCID search ↗
  10. BotSim: LLM-Powered Malicious Social Botnet Simulation
    AAAI 2025 ·
    Boyu Qiao
    DBLP profile ↗ORCID search ↗
  11. Capture the Key in Reasoning to Enhance CoT Distillation Generalization
    ACL 2025 ·
    Chengwei Dai
    DBLP profile ↗ORCID search ↗
  12. CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
    NAACL 2025 ·
    Zhenpeng Su
    DBLP profile ↗ORCID search ↗
  13. Chain of Attack: Hide Your Intention through Multi-Turn Interrogation
    ACL 2025 ·
    Xikang Yang
    DBLP profile ↗ORCID search ↗
  14. DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
    EMNLP 2025 ·
    Minxuan Lv
    DBLP profile ↗ORCID search ↗
  15. Dynamic Simulation Framework for Disinformation Dissemination and Correction With Social Bots
    EMNLP 2025 ·
    Boyu Qiao
    DBLP profile ↗ORCID search ↗
  16. Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models
    AAAI 2025 ·
    Han Cao
    DBLP profile ↗ORCID search ↗
  17. Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models
    EMNLP 2025 ·
    Lijia Lv
    DBLP profile ↗ORCID search ↗
  18. Impartial Multi-task Representation Learning via Variance-invariant Probabilistic Decoding
    ACL 2025 ·
    Dou Hu
    DBLP profile ↗ORCID search ↗
  19. LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions
    NeurIPS 2025 ·
    Chaochen Gao
    DBLP profile ↗ORCID search ↗
  20. LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
    EMNLP 2025 ·
    Peng Wang
    DBLP profile ↗ORCID search ↗
  21. NExtLong: Toward Effective Long-Context Training without Long Documents
    ICML 2025 ·
    Chaochen Gao
    DBLP profile ↗ORCID search ↗
  22. Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model
    ICLR 2025 ·
    Chaochen Gao
    DBLP profile ↗ORCID search ↗
  23. Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigation
    EMNLP 2025 ·
    Haonan Sheng
    DBLP profile ↗ORCID search ↗
  24. Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detection
    ACL 2025 ·
    Lingwei Wei
    DBLP profile ↗ORCID search ↗
  25. Structure-aware Propagation Generation with Large Language Models for Fake News Detection
    EMNLP 2025 ·
    Mengyang Chen
    DBLP profile ↗ORCID search ↗
  26. Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
    AAAI 2025 ·
    Guangyuan Ma
    DBLP profile ↗ORCID search ↗
  27. Visual Perception Uncertainty Learning for Hallucination Detection in Large Vision-Language Models
    ACM MM 2025 ·
    Runze Zhao
    DBLP profile ↗ORCID search ↗
  28. Breaking the Weak Semantics Bottleneck of Transformers in Time Series Forecasting
    ECAI 2024 ·
    Ziang Yang
    DBLP profile ↗ORCID search ↗
  29. Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
    NAACL 2024 ·
    Zhenpeng Su
    DBLP profile ↗ORCID search ↗
  30. Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval
    SIGIR 2024 ·
    Guangyuan Ma
    DBLP profile ↗ORCID search ↗
  31. Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction
    EMNLP 2024 ·
    Jinchuan Zhang
    DBLP profile ↗ORCID search ↗
  32. Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
    EMNLP 2024 ·
    Chengwei Dai
    DBLP profile ↗ORCID search ↗
  33. Information Diffusion Prediction with Graph Neural Ordinary Differential Equation Network
    ACM MM 2024 ·
    Ding Wang
    DBLP profile ↗ORCID search ↗
  34. MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
    NAACL 2024 ·
    Zhenpeng Su
    DBLP profile ↗ORCID search ↗
  35. Propagation Structure-Semantic Transfer Learning for Robust Fake News Detection
    ECML-PKDD 2024 ·
    Mengyang Chen
    DBLP profile ↗ORCID search ↗
  36. Representation Learning with Conditional Information Flow Maximization
    ACL 2024 ·
    Dou Hu
    DBLP profile ↗ORCID search ↗
  37. Structured Probabilistic Coding
    AAAI 2024 ·
    Dou Hu
    DBLP profile ↗ORCID search ↗
  38. Uncertainty-Guided Modal Rebalance for Hateful Memes Detection
    ACL 2024 ·
    Chuanpeng Yang
    DBLP profile ↗ORCID search ↗