One Fabrication Is Enough: A Fake News Article Changes the Forecasts of LLM Forecasting Systems
cs.CR, cs.CL, cs.LG
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Forecasting Future World Events with Neural Networks
- Approaching Human-Level Forecasting with Language Models
- AIA Forecaster: Technical Report
- PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Certifiably Robust RAG against Retrieval Corruption
- GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search
- Practical Poisoning Attacks against Retrieval-Augmented Generation
- SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
- AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
- Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Trading
- Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
- TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
- PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption
- Reducing Certified Regression to Certified Classification for General Poisoning Attacks
- Corrective Retrieval Augmented Generation
- All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting
- Command A: An Enterprise-Ready Large Language Model
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data