EST-PRM stress-tests five PRM models on 4,687 reasoning chains from MATH-500, GSM8K, and PRMBench using three label-preserving transformations and reports model-specific vulnerability patterns.
hub Canonical reference
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Canonical reference. 86% of citing Pith papers cite this work as background.
47
Pith papers citing it
Background
86% of classified citations
abstract
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this popularity, there has been relatively little public work systematizing its flaws. In this paper, we (1) survey open problems and fundamental limitations of RLHF and related methods; (2) overview techniques to understand, improve, and complement RLHF in practice; and (3) propose auditing and disclosure standards to improve societal oversight of RLHF systems. Our work emphasizes the limitations of RLHF and highlights the importance of a multi-faceted approach to the development of safer AI systems.
hub tools
citation-role summary
background 7
citation-polarity summary
roles
background 7representative citing papers
Self-evolving rubric with anti-gaming fitness reveals that objective capability scaling fails to transfer to subjective LLM behaviors, with advice-restraint as the universal lowest dimension that can regress.
Base model text evades AI detectors better than instruction-tuned text, and the HIP method strengthens this trade-off across model sizes.
Moira parameterizes hierarchical RL policies for pair trading with LLMs and adapts them via prompt updates based on trajectory and episode feedback, outperforming baselines on real market data.
RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
Primal-dual policy gradient algorithms achieve global non-asymptotic convergence for safe RLHF cast as infinite-horizon discounted CMDPs without fitting reward models.
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
TOMPA performs black-box adversarial optimization in token space to discover non-linguistic patterns that nearly double the reward scores of GPT-5 answers on Skywork-Reward-V2 while producing gibberish text.
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Open-ended preference data reveals substantial plurality in what people want from AI and divergent interpretations of shared values such as truthfulness.
Combines LTL formal methods with LLMs for auditing, predictive monitoring, and runtime intervention on temporally extended behavioral constraints, outperforming LLM baselines and reducing violations.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
LLMs show partial internal coherence in medical decisions but frequently fail to accurately report their preferences or adopt user-directed ones via prompting.
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
Dr. Post-Training reframes general data as a data-induced regularizer for LLM post-training updates, yielding a family of methods that outperform data-selection baselines on SFT, RLHF, and RLVR tasks.
Sparse autoencoders isolate unstable features in reward model representations and enable two mitigation techniques that reduce preference errors on perturbed inputs without retraining.
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement lower bounds.
A framework treating clinician overrides as implicit preferences to jointly train reward and capability models for clinical AI, with a taxonomy and alternating optimization to prevent suppression bias.
The First Fundamental Theorem of Welfare Economics holds for autonomy-complete competitive equilibria that are autonomy-Pareto efficient, with the classical version recovered in the low-autonomy limit.
PlanGuard cuts indirect prompt injection attack success rate to 0% on the InjecAgent benchmark by verifying agent actions against a user-instruction-only plan while keeping false positives at 1.49%.
ORPO is most effective at misaligning LLMs while DPO excels at realigning them, though it reduces utility, revealing an asymmetry between attack and defense methods.
ETS performs training-free RL alignment for language models by energy-guided test-time scaling with Monte Carlo energy estimation and importance sampling acceleration.
A gamified system with multiple LLM agents of varied personalities gathers interaction data to produce more effective and interpretable Big Five personality assessments than single-context methods.
citing papers explorer
-
Moira: Language-driven Hierarchical Reinforcement Learning for Pair Trading
Moira parameterizes hierarchical RL policies for pair trading with LLMs and adapts them via prompt updates based on trajectory and episode feedback, outperforming baselines on real market data.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems
Combines LTL formal methods with LLMs for auditing, predictive monitoring, and runtime intervention on temporally extended behavioral constraints, outperforming LLM baselines and reducing violations.
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Active teacher selection for reward learning
The Hidden Utility Bandit (HUB) framework models teacher heterogeneity in reward learning and supports active teacher selection algorithms that outperform baselines in paper recommendation and COVID-19 vaccine testing domains.
-
Echo: Learning from Experience Data via User-Driven Refinement
Echo is a framework that harvests user-driven refinements of agent proposals as training signals to align models with real-world needs, demonstrated by raising code completion acceptance from 25.7% to 35.7% in production.
-
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Data-centric filtering yields an 80K preference dataset and reward models that lead RewardBench while boosting other top entries.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
-
Beyond Context: Large Language Models' Failure to Grasp Users' Intent
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.
-
Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.