Study evaluates new models using human feedback from another model.
problem Evaluate a new model using human feedback collected for another model.
method Formalize problem, propose model-based and model-free estimators, analyze unbiasedness, and empirically evaluate.
result Proposed estimators can predict absolute values, rank, and optimize evaluated policies.
RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.
problem Failure of reinforcement learning from human feedback in partially observable environments.
method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.
result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.
PILAF optimizes reward models from human feedback for better policy alignment.
problem Creating accurate reward models from human feedback for policy optimization.
method Policy-Interpolated Learning for Aligned Feedback (PILAF) that explicitly aligns preference learning with maximizing underlying oracle reward.
result PILAF is optimal from both optimization and statistical perspectives, demonstrating strong performance in RLHF settings.
Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies i…
Active learning framework for optimizing human preferences in reinforcement learning.
problem Selecting most informative feedback for training models of human preferences.
method Proposes an active learning framework to collect preferential feedback online or offline.
result Errors in DPO logit estimates diminish with more feedback.
Efficiently identifies good policies by choosing contexts for human feedback.
problem Efficiently identifying good policies in applications with high feedback costs.
method Introduces offline contextual dueling bandit setting and an upper-confidence-bound style algorithm.
result Proves a regret bound and shows superior performance over uniformly sampled contexts.
LoCo-RLHF models diverse human feedback with contextual information.
problem Heterogeneous human feedback from diverse contexts and preferences.
method Low-rank contextual preference model, PRS policy.
result LoCo-RLHF achieves tighter sub-optimality gap than existing methods.
This paper argues for more realistic human models in RL.
problem Current RL models oversimplify human feedback, ignoring personal, contextual, and dynamic aspects.
method Calls for interdisciplinary research on human feedback in RL.
result Realistic human models are needed for robust human-in-the-loop RL systems.
This work compares human feedback methods for reward learning in bandits.
problem Understanding how human feedback affects the performance of reward learning methods.
method Theoretical comparison of human feedback approaches in offline contextual bandits.
result Human bias and uncertainty in feedback modeling impact the theoretical guarantees of reward learning methods.
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator,…
Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the machine to adapt to the users' intentions and preferences. Often, this takes the…
Unified LP framework for offline reward learning from human demonstrations and feedback.
problem Reward learning from human demonstrations and feedback with robustness and sample efficiency.
method A novel linear programming framework for offline reward learning.
result Unified LP framework achieves better performance compared to MLE.
Dual active learning improves RLHF by selecting optimal conversations and teachers.
problem Efficiently aligning LLMs with human preferences using RLHF from feedback.
method Offline RL for conversation and teacher selection, dual active reward learning, pessimistic RL.
result The proposed algorithm achieves minimal generalized variance and outperforms state-of-the-arts.
This thesis tackles learning reward functions from human comparative feedback.
problem Designing reward functions for complex tasks is challenging and humans often provide suboptimal demonstrations.
method Proposes learning reward functions from comparative feedback (pairwise comparisons, best-of-many choices, rankings, scaled comparisons) and active learning techniques.
result Demonstrates the effectiveness of learning reward functions from comparative feedback in various domains.
Hölder-DPO aligns models robustly with noisy human feedback.
problem No existing alignment methods can handle severe label noise.
method Proposes Hölder-DPO, a principled alignment loss with provable redescending property.
result Hölder-DPO enables scalable human feedback valuation and improves model alignment.
A new approach to fine-tuning LLMs with human feedback.
problem Inability of current reward models to fully represent human preferences.
method Introducing NLHF, a new pipeline for LLM fine-tuning using pairwise human feedback.
result NLHF produces a sequence of policies converging to the regularized Nash equilibrium.
Efficiently identifies good policies by choosing contexts for human feedback.
problem Efficiently acquiring human feedback for preference alignment in large language models.
method Formalizes active exploration as a dueling bandit problem and proposes an active exploration algorithm with a polynomial worst-case regret bound.
result Proposed method outperforms baselines with limited human preferences on various language models and datasets.
Neural algorithms optimize arm selection with human preference feedback for complex reward functions.
problem Optimizing arm selection with noisy human preference feedback for complex, non-linear reward functions.
method Neural network to estimate reward function using preference feedback, upper confidence bound and Thompson sampling algorithms.
result Sub-linear regret guarantees for efficient arm selection in contextual dueling bandits.
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of time while efficiently leveraging the sparse feedback a human trainer is capable o…
AI assistants often give convincing but incorrect responses to match user beliefs.
problem Sycophancy in AI assistants that use human feedback.
method Examined five AI assistants across four tasks, analyzed human preference data, and compared model outputs against preference models.
result Sycophancy is a general behavior of AI assistants, driven in part by human preference judgments.
Enhances AI models with human feedback for noisy data.
problem Improving AI model alignment with human feedback in noisy environments.
method Two-stage SL+LHF framework connecting machine learning with human feedback.
result The LNCA ratio identifies conditions for SL+LHF superiority over pure SL.
Paper presents a novel framework for OOD learning with human feedback.
problem Multifaceted challenges of OOD generalization and detection.
method Selective human feedback for labeling a small number of informative samples from wild data distribution.
result Enhanced robustness and precision in handling OOD scenarios.
Access to high-quality education at scale is limited by the difficulty of providing student feedback on open-ended assignments in structured domains like computer programming, graphics, and short response questions. This problem has proven to be exceptionally difficult: for humans, it requires large amounts of manual w…
SLHF uses sequential game theory to optimize preferences from human feedback.
problem Optimizing preferences from human feedback in sequential settings.
method SLHF frames the problem as a sequential-move game between Leader and Follower, decomposing the optimization into refinement and adversarial optimization.
result SLHF achieves strong alignment across diverse preference datasets and scales to large models.
Method tackles uncertainty in reward models for LLMs from heterogeneous human feedback.
problem Uncertainty in reward models for LLMs from heterogeneous human feedback.
method Heterogeneous preference framework and alternating gradient descent algorithm.
result Established theoretical guarantees for estimator convergence and asymptotic distribution.
The paper tackles learning from imperfect human feedback, especially in dueling bandit problems.
problem Learning from human feedback that can be irrational or imperfect.
method Developed a Robustified Stochastic Mirror Descent for Imperfect Dueling (RoSMID) algorithm.
result Achieved nearly optimal regret for dueling bandit problems under imperfect human feedback.
RLHF uses human feedback to train AI models, posing statistical challenges.
problem Aligning AI models with human preferences using noisy, subjective feedback.
method Supervised fine-tuning, reward modeling, policy optimization, statistical ideas.
result Statistical methods for reward function learning and policy optimization.
Proposes a new theoretical framework for PbRL that requires less human feedback.
problem Lack of theoretical work capturing practical PbRL frameworks.
method Introduces a reward-agnostic PbRL framework that acquires exploratory trajectories before human feedback.
result Demonstrates improved sample complexity for learning optimal policies in linear and low-rank MDPs.
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…
In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration. In this way, we leverage the advantages of both these representations, i.e., we learn the policy u…
Learning from human feedback is a viable alternative to control design that does not require modelling or control expertise. Particularly, learning from corrective advice garners advantages over evaluative feedback as it is a more intuitive and scalable format. The current state-of-the-art in this field, COACH, has pro…
Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.
problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.
Develops a new model for RLHF accounting for partially observed states and intermediate feedback.
problem Lack of models for partially observed states and intermediate feedback in RLHF.
method PORRL model with cardinal and dueling feedback methods.
result Demonstrates improved learning and alignment with new model-based and model-free methods.
The abstract explores connections between reinforcement learning, scaling, and diffusion.
problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.
Develops methods to correct bias in AI feedback for more accurate alignment.
problem Systematic bias in AI feedback compared to human labels.
method Two debiased alignment methods: DDPO and DIPO.
result Methods improve alignment efficiency and performance close to human-labeled data.
New algorithm learns human preferences from few comparisons efficiently.
problem Learning human preferences from limited comparison feedback.
method Formulated as D-optimal design for Plackett-Luce model, solved using randomized Frank-Wolfe algorithm.
result Proposed algorithm efficiently solves D-optimal design problem for Plackett-Luce objective.
Study preference-based reinforcement learning in episodic kernel MDPs.
problem Learning from episodic human preferences in reinforcement learning.
method Developed preference-based value estimation and confidence sets for kernel-based MDPs.
result Proved high-probability regret bounds that converge to optimal policy value.
CausalRM models rewards from user feedback, overcoming noise and bias.
problem Aligning language models with user preferences from noisy, biased feedback.
method Causal-theoretic reward modeling framework addressing noise and bias in observational feedback.
result CausalRM learns accurate reward signals from noisy and biased observational feedback.
In semantic parsing for question-answering, it is often too expensive to collect gold parses or even gold answers as supervision signals. We propose to convert model outputs into a set of human-understandable statements which allow non-expert users to act as proofreaders, providing error markings as learning signals to…
Paper proposes a robust RLHF algorithm for LLMs, improving response preference over baselines.
problem Reward model misspecifications in RLHF for LLMs.
method Proposes a robust algorithm to reduce reward and policy estimator variance, theoretically and empirically validated.
result Consistently outperforms existing methods on LLM benchmark datasets, favoring 77-81% of responses over baselines.
A new method for RLHF using proximal point Nash learning.
problem Capturing real human preferences in RLHF.
method Proximal point Nash learning, embedding self-play updates into a proximal point framework.
result High-probability last-iterate convergence for the combined method.
Hybrid approach combines user feedback and machine learning for predicting user satisfaction.
problem Measuring user satisfaction in large-scale conversational agent systems.
method Fusion of explicit user feedback and predictions from two machine-learned models trained on different data types.
result Hybrid approach significantly improves user satisfaction predictions.
Paper develops methods to optimize policies directly from human feedback without reward inference.
problem Challenges in RLHF, including reward model overfitting and distribution shift.
method Develops two algorithms for RLHF without reward inference, using zeroth-order gradient approximators.
result Establishes polynomial convergence rates and outperforms existing methods in numerical experiments.
The paper analyzes RLHF with human feedback and provides convergence results for MLE and pessimistic MLE.
problem Improving RLHF with human feedback from pairwise or K-wise comparisons. method Theoretical framework for RLHF with convergence analysis of MLE and pessimistic MLE.
result MLE fails but pessimistic MLE provides improved policies under certain coverage assumptions.
UCFE benchmarks LLMs in financial tasks with human feedback.
problem Evaluating LLMs' financial task performance and user satisfaction.
method Hybrid approach combining human expert evaluations and dynamic interactions.
result Significant alignment between benchmark scores and human preferences (Pearson correlation coefficient of 0.78).
Algorithm learns actions from past states in complex tasks.
problem Learning policies from human feedback is expensive.
method Combining learned feature encoder with inverse models to simulate past actions.
result Algorithm can infer specific skills from single state.
Paper proposes a new RLHF framework for human preference learning.
problem Handling dependent online human preference outcomes with dynamic contexts.
method Two-stage algorithm with ε-greedy followed by exploitation; anti-concentration inequalities and matrix martingale concentration techniques. result Our method achieves optimal regret bound and asymptotic normality of estimators.
Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human …