Unraveling Misinformation Propagation in LLM Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918146124808192 |
|---|---|
| author | Feng, Yiyang Wang, Yichen Cui, Shaobo Faltings, Boi Lee, Mina Zhou, Jiawei |
| author_facet | Feng, Yiyang Wang, Yichen Cui, Shaobo Faltings, Boi Lee, Mina Zhou, Jiawei |
| contents | Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning, positioning them as promising tools for supporting human problem-solving. However, what happens when their performance is affected by misinformation, i.e., incorrect inputs introduced by users due to oversights or gaps in knowledge? Such misinformation is prevalent in real-world interactions with LLMs, yet how it propagates within LLMs' reasoning process remains underexplored. Focusing on mathematical reasoning, we present a comprehensive analysis of how misinformation affects intermediate reasoning steps and final answers. We also examine how effectively LLMs can correct misinformation when explicitly instructed to do so. Even with explicit instructions, LLMs succeed less than half the time in rectifying misinformation, despite possessing correct internal knowledge, leading to significant accuracy drops (10.02% - 72.20%), and the degradation holds with thinking models (4.30% - 19.97%). Further analysis shows that applying factual corrections early in the reasoning process most effectively reduces misinformation propagation, and fine-tuning on synthesized data with early-stage corrections significantly improves reasoning factuality. Our work offers a practical approach to mitigating misinformation propagation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18555 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unraveling Misinformation Propagation in LLM Reasoning Feng, Yiyang Wang, Yichen Cui, Shaobo Faltings, Boi Lee, Mina Zhou, Jiawei Computation and Language Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning, positioning them as promising tools for supporting human problem-solving. However, what happens when their performance is affected by misinformation, i.e., incorrect inputs introduced by users due to oversights or gaps in knowledge? Such misinformation is prevalent in real-world interactions with LLMs, yet how it propagates within LLMs' reasoning process remains underexplored. Focusing on mathematical reasoning, we present a comprehensive analysis of how misinformation affects intermediate reasoning steps and final answers. We also examine how effectively LLMs can correct misinformation when explicitly instructed to do so. Even with explicit instructions, LLMs succeed less than half the time in rectifying misinformation, despite possessing correct internal knowledge, leading to significant accuracy drops (10.02% - 72.20%), and the degradation holds with thinking models (4.30% - 19.97%). Further analysis shows that applying factual corrections early in the reasoning process most effectively reduces misinformation propagation, and fine-tuning on synthesized data with early-stage corrections significantly improves reasoning factuality. Our work offers a practical approach to mitigating misinformation propagation. |
| title | Unraveling Misinformation Propagation in LLM Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.18555 |