arXiv (All)
open access
Fooling Reward Models with Gibberish: Adversarial Examples Beyond the Semantic Regime
Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF). We show that leading RMs can assign higher scores to gibberish than to meaningful reference answers. To systematically discover such inputs, we introduce Token Mapping Perturbation Attac
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ASCT: Attentive Search over Counterfactual Trees for Credit Assignment in Agentic Reinforcement Learning#1129812
- RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation#1234487
- Reverse Turing Tests for Human-Machine Task Suitability Assessments Should be Profile-Driven#204160
- Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR#1131563
- When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models#819067
Record · ID 1537192
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive