Preemptive Detection and Correction of Misaligned Actions in LLM Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909815581704192 |
|---|---|
| author | Fang, Haishuo Zhu, Xiaodan Gurevych, Iryna |
| author_facet | Fang, Haishuo Zhu, Xiaodan Gurevych, Iryna |
| contents | Deploying LLM-based agents in real-life applications often faces a critical challenge: the misalignment between agents' behavior and user intent. Such misalignment may lead agents to unintentionally execute critical actions that carry negative outcomes (e.g., accidentally triggering a "buy-now" in web shopping), resulting in undesirable or even irreversible consequences. Although addressing these issues is crucial, the preemptive detection and correction of misaligned actions remains relatively underexplored. To fill this gap, we introduce InferAct, a novel approach that leverages the belief reasoning ability of LLMs, grounded in Theory-of-Mind, to detect misaligned actions before execution. Once the misalignment is detected, InferAct alerts users for timely correction, preventing adverse outcomes and enhancing the reliability of LLM agents' decision-making processes. Experiments on three widely used tasks demonstrate that InferAct achieves up to 20% improvements on Marco-F1 against baselines in misaligned action detection. An in-depth evaluation of misalignment correction further highlights InferAct's effectiveness in improving agent alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11843 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Preemptive Detection and Correction of Misaligned Actions in LLM Agents Fang, Haishuo Zhu, Xiaodan Gurevych, Iryna Computation and Language Artificial Intelligence Deploying LLM-based agents in real-life applications often faces a critical challenge: the misalignment between agents' behavior and user intent. Such misalignment may lead agents to unintentionally execute critical actions that carry negative outcomes (e.g., accidentally triggering a "buy-now" in web shopping), resulting in undesirable or even irreversible consequences. Although addressing these issues is crucial, the preemptive detection and correction of misaligned actions remains relatively underexplored. To fill this gap, we introduce InferAct, a novel approach that leverages the belief reasoning ability of LLMs, grounded in Theory-of-Mind, to detect misaligned actions before execution. Once the misalignment is detected, InferAct alerts users for timely correction, preventing adverse outcomes and enhancing the reliability of LLM agents' decision-making processes. Experiments on three widely used tasks demonstrate that InferAct achieves up to 20% improvements on Marco-F1 against baselines in misaligned action detection. An in-depth evaluation of misalignment correction further highlights InferAct's effectiveness in improving agent alignment. |
| title | Preemptive Detection and Correction of Misaligned Actions in LLM Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.11843 |