| _version_ | 1866902337372553216 |
|---|---|
| author | Liliz-lab harmonia-ml |
| author_facet | Liliz-lab harmonia-ml |
| contents | <p>This dataset accompanies the paper "Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities" (Zhang et al., 2025). It contains behavioral and simulated data from experiments evaluating the decision-making robustness of large language models (LLMs) under adversarial and dynamic conditions.</p> <p>The dataset includes results from two canonical paradigms:</p> <p>Two-Armed Bandit Task — tests exploration–exploitation balance across different models and decoding settings (e.g., temperature, top-p).</p> <p>Multi-Round Trust Task (MRTT) — examines cooperative and adaptive decision-making in social exchange between LLMs and adversarial agents.</p> <p>Each file records trial-level choices, rewards, and model parameters (e.g., temperature, top-p, model name), with aggregated performance metrics for human and model comparisons. The dataset supports reproducible behavioral analyses and provides a foundation for studying model-specific susceptibilities to manipulation, rigidity, and fairness recognition.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17398584 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Liliz-lab/llm-advers-eval: LLM Adversarial Evaluation (Zhang et al., 2025) Liliz-lab harmonia-ml <p>This dataset accompanies the paper "Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities" (Zhang et al., 2025). It contains behavioral and simulated data from experiments evaluating the decision-making robustness of large language models (LLMs) under adversarial and dynamic conditions.</p> <p>The dataset includes results from two canonical paradigms:</p> <p>Two-Armed Bandit Task — tests exploration–exploitation balance across different models and decoding settings (e.g., temperature, top-p).</p> <p>Multi-Round Trust Task (MRTT) — examines cooperative and adaptive decision-making in social exchange between LLMs and adversarial agents.</p> <p>Each file records trial-level choices, rewards, and model parameters (e.g., temperature, top-p, model name), with aggregated performance metrics for human and model comparisons. The dataset supports reproducible behavioral analyses and provides a foundation for studying model-specific susceptibilities to manipulation, rigidity, and fairness recognition.</p> |
| title | Liliz-lab/llm-advers-eval: LLM Adversarial Evaluation (Zhang et al., 2025) |
| url | https://doi.org/10.5281/zenodo.17398584 |