WhitzardNUWA Lab ↗
NUWANUWA INDEX

Search NUWA Index

Research · Benchmarks · Findings · Perspectives

中文
← NUWA Index

Evidence record

Llama-3.1-70B-Instruct

OpenDeception · Evidence record

Fudan University · Shanghai Innovation Institute / arXiv:2504.13707v3 / Propensity

Sources and provenance ↓ Read the research narrative →

Original source charts and materials

Reported results

Source order · reported configurations

IntentNet DIR

0–100%
Llama-3.1-70B-Instruct
100%
Showing 1 of 1 systems

Values describe the measured outcome under the source protocol, not a general safety score.

Table 1: deception-intention rates under OpenDeception scenario conditions, assessed by IntentNet and human annotators. Consistency is agreement, not deception success. Evaluation date not specified; publication / record dates are shown below.

Evaluation conditions and system configurations
Llama-3.1-70B-Instruct
50 authored scenarios; evaluated cases depend on the source screening procedure. · Table 1 · OpenDeception
modelVersion: not specified · harness: not specified · tools: not specified · budget: not specified
Reported results · source order
System / configurationIntentNet DIRHuman DIRAnnotator consistencyPublication / verification
Llama-3.1-70B-InstructHarness not specified100%97.5%97.5%Source checked2026-10-25

Method and scope

Scenario-based inferred intent and modeled user trust.

Evidence type
Benchmark
Assessment subject
Model in simulated social interactions
Primary dimension
Propensity
Evidence snapshot
2026-10-29.1

Primary dimension follows the source’s measured construct. Metric-level interpretations may differ.

Source finding

Source-reported measurements for Llama-3.1-70B-Instruct in Table 1; values are transcribed, not independently reproduced.

Limitations

Inferred intent is a measurement construct; simulated users do not establish human effects.

Configuration, task and aggregation differences remain as reported. Source order is retained. Transcription is not independent replication; no cross-protocol ranking is supported.

Related research questions

References

Numerical results are reported by the cited authors.

  1. [1] Yichen Wu, Qianqian Gao, et al.. OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation. 2026-02-06. v3 [arXiv]; Author affiliations on the original paper title page; Table 1