AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914470866976768 |
|---|---|
| author | Song, Hongru Liu, Yu-An Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Fan, Yixing Cheng, Xueqi |
| author_facet | Song, Hongru Liu, Yu-An Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Fan, Yixing Cheng, Xueqi |
| contents | Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base poisoning attacks in RAG, where an attacker injects malicious content into the retrieval corpus, which is then naturally surfaced by the retriever and consumed by the LLM during reasoning. Unlike prior work that floods the corpus with poisoned documents, we propose AdversarialCoT, a query-specific attack that poisons only a single document in the corpus. AdversarialCoT first extracts the target LLM's reasoning framework to guide the construction of an initial adversarial chain-of-thought (CoT). The adversarial document is iteratively refined through interactions with the LLM, progressively exposing and exploiting critical reasoning vulnerabilities. Experiments on benchmark LLMs show that a single adversarial document can significantly degrade reasoning accuracy, revealing subtle yet impactful weaknesses. This study exposes security risks in RAG systems and provides actionable insights for designing more robust LLM reasoning pipelines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12201 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning Song, Hongru Liu, Yu-An Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Fan, Yixing Cheng, Xueqi Information Retrieval Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base poisoning attacks in RAG, where an attacker injects malicious content into the retrieval corpus, which is then naturally surfaced by the retriever and consumed by the LLM during reasoning. Unlike prior work that floods the corpus with poisoned documents, we propose AdversarialCoT, a query-specific attack that poisons only a single document in the corpus. AdversarialCoT first extracts the target LLM's reasoning framework to guide the construction of an initial adversarial chain-of-thought (CoT). The adversarial document is iteratively refined through interactions with the LLM, progressively exposing and exploiting critical reasoning vulnerabilities. Experiments on benchmark LLMs show that a single adversarial document can significantly degrade reasoning accuracy, revealing subtle yet impactful weaknesses. This study exposes security risks in RAG systems and provides actionable insights for designing more robust LLM reasoning pipelines. |
| title | AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.12201 |