Explore/benchmark/AI Safety via Debate is Compromised by Cognitive Biases
A

Gefei Liu, Sonya Rashkovan, Sophia Lloyd George, Isaac Sheidlower, Serena Booth/AI Safety via Debate is Compromised by Cognitive BiasesUnknown

Reinforcement learning from human feedback (RLHF) has played a central role in making large language models responsive to human instructions. However, human evaluators often favor flattering or persuasive responses over truthful ones, creating incentives for models to appeal to evaluators at the expense of accuracy. AI safety via debate has been proposed as a way to improve the supervision of language models: in this paradigm, two agents argue opposing positions and challenge each other's claims, potentially exposing falsehoods to the adjudicator. A central premise of AI safety via debate is that truthful arguments are easier to defend than false ones under adversarial scrutiny. In this work, we investigate whether this advantage persists when debaters use rhetorical strategies that exploit biases in human judgment. Inspired by competitive debate, we construct 68 LLM-generated dialogues about detective mysteries with known culprits, spanning four interventions: anchoring, fallacy oversight, pro-jargon, and verbosity. We apply each intervention to either the side advocating for the true culprit or the side advocating for an innocent suspect, allowing us to distinguish influence on adjudication from correctness. In a study with 369 participants, we find that, pooled across bias types, these interventions significantly shift judgments toward the manipulated side. These findings expose a vulnerability in debate-based supervision: human adjudication is sensitive to manipulative rhetorical strategies.

benchmark
GitHubCompare
Refreshed 11h ago
OverviewActivity52wAlternativesDocs
Stars0
Forks0
HF Downloads—30d
Last commit—
Refreshed11h ago
Project healthUnknownNo activity data.
Production readinessResearch / EarlyBest for exploration and prototyping.
Risk notesUnknown licenseVerify license before production use.
AgentHub Score
55 / 100
Composite score from 6 signals. How we score →
Active project
55Score
Growth
40C
Activity
30C
Documentation
70C+
Maturity
45C
Community
42C
Production
58C
GitHub stars · 0 days observed0 not enough history
snapshots
not enough history
Repository activity · 0 days observednot enough history from pushed_at
inactivepushed
not enough history
not enough history
Practical assessment
Should you use it?

✓ Best for

  • Research and experimentation
  • Prototype development
  • Learning agentic patterns

◎ Strengths

  • Active community
  • Open source
  • Well-documented API

✕ Not ideal for

  • Untested at scale without validation
  • Teams without AI/ML expertise

⚠ Watch-outs

  • Review changelog before updating
  • Verify license for commercial use
Technical details
What's inside
Language—
License—
Sourcearxiv
Open source✗ No
Commercial use—
Docs—
Demo—

AgentHub Score

55
Score 55/100
Below average

Alternatives

R
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems
0 · benchmark
55
C
Commitment To Cooperation With Self-Negotiated Contracts
0 · benchmark
55
E
Exploring Structures in Physics Problems: Can AI Agents Discover Statistical Mechanical Mappings?
0 · benchmark
55
C
Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation
0 · benchmark
55Compare all →

Recent activity

Latest commit ——
Indexed by AgentHub crawler11h ago
Monitor for new releasesongoing