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.
50
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.
Preference poisoning against log-linear DPO reduces to a binary sparse approximation problem solved by lattice-reduction (BAL-A) and matching-pursuit (BMP-A) algorithms that carry recovery guarantees.
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.
Characterizes spurious correlation mechanisms in preference optimization via mean spurious bias and causal-spurious correlation leakage, demonstrates irreducible vulnerability to distribution shift, and introduces tie training as selective mitigation with validation on log-linear models and empirica
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.
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
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%.
citing papers explorer
-
EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing
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.
-
Efficient Preference Poisoning Attack on Offline RLHF
Preference poisoning against log-linear DPO reduces to a binary sparse approximation problem solved by lattice-reduction (BAL-A) and matching-pursuit (BMP-A) algorithms that carry recovery guarantees.
-
Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback
Primal-dual policy gradient algorithms achieve global non-asymptotic convergence for safe RLHF cast as infinite-horizon discounted CMDPs without fitting reward models.
-
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
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.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
Characterizes spurious correlation mechanisms in preference optimization via mean spurious bias and causal-spurious correlation leakage, demonstrates irreducible vulnerability to distribution shift, and introduces tie training as selective mitigation with validation on log-linear models and empirica
-
Can Revealed Preferences Clarify LLM Alignment and Steering?
LLMs show partial internal coherence in medical decisions but frequently fail to accurately report their preferences or adopt user-directed ones via prompting.
-
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
-
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
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.
-
Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders
Sparse autoencoders isolate unstable features in reward model representations and enable two mitigation techniques that reduce preference errors on perturbed inputs without retraining.
-
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
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.
-
Learning from Disagreement: Clinician Overrides as Implicit Preference Signals for Clinical AI in Value-Based Care
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.
-
ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment
ETS performs training-free RL alignment for language models by energy-guided test-time scaling with Monte Carlo energy estimation and importance sampling acceleration.
-
Exploring the Secondary Risks of Large Language Models
Introduces secondary risks as a new class of LLM failures from benign prompts, defines two primitives, proposes SecLens search framework, and releases SecRiskBench showing risks are widespread across 16 models.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
In-Context Reward Adaptation for Robust Preference Modeling
Transformer model with response-time auxiliary input adapts reward models to unseen human preference domains via in-context learning from demonstrations.
-
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
Reflector internalizes step-wise self-reflection in LLMs via teacher-guided SFT then RL with outcome and validity rewards, claiming over 90% defense success against indirect jailbreaks plus utility gains like 5.85% on GSM8K.
-
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
RAFT aligns generative models by ranking samples with a reward model and fine-tuning only on the top-ranked outputs, reporting gains on reward scores and automated metrics for LLMs and diffusion models.
-
ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks
ClaHF converts instance labels into preference signals via candidate predictions and a reward model, then applies RL optimization to improve text classification accuracy and calibration.
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.