Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
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_ | 1866908773823545344 |
|---|---|
| author | Liu, Yi Liu, Xiangyu Sun, Zequn Hu, Wei |
| author_facet | Liu, Yi Liu, Xiangyu Sun, Zequn Hu, Wei |
| contents | Large reasoning models (LRMs) have shown remarkable progress on complex reasoning tasks. However, some questions posed to LRMs are inherently unanswerable, such as math problems lacking sufficient conditions. We find that LRMs continually fail to provide appropriate abstentions when confronted with these unanswerable questions. In this paper, we systematically analyze, investigate, and resolve this issue for trustworthy AI. We first conduct a detailed analysis of the distinct response behaviors of LRMs when facing unanswerable questions. Then, we show that LRMs possess sufficient cognitive capabilities to recognize the flaws in these questions. However, they fail to exhibit appropriate abstention behavior, revealing a misalignment between their internal cognition and external response. Finally, to resolve this issue, we propose a lightweight, two-stage method that combines cognitive monitoring with inference-time intervention. Experimental results demonstrate that our method significantly improves the abstention rate while maintaining the overall reasoning performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18760 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models Liu, Yi Liu, Xiangyu Sun, Zequn Hu, Wei Artificial Intelligence Computation and Language Large reasoning models (LRMs) have shown remarkable progress on complex reasoning tasks. However, some questions posed to LRMs are inherently unanswerable, such as math problems lacking sufficient conditions. We find that LRMs continually fail to provide appropriate abstentions when confronted with these unanswerable questions. In this paper, we systematically analyze, investigate, and resolve this issue for trustworthy AI. We first conduct a detailed analysis of the distinct response behaviors of LRMs when facing unanswerable questions. Then, we show that LRMs possess sufficient cognitive capabilities to recognize the flaws in these questions. However, they fail to exhibit appropriate abstention behavior, revealing a misalignment between their internal cognition and external response. Finally, to resolve this issue, we propose a lightweight, two-stage method that combines cognitive monitoring with inference-time intervention. Experimental results demonstrate that our method significantly improves the abstention rate while maintaining the overall reasoning performance. |
| title | Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.18760 |