Andi Peng

Stephen Casper, Xander Davies, Claudia Shi et al. · berkeley, eth-zurich

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.

Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller et al. · berkeley, cambridge

Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the similarity between the representations formed by these diverse systems? Do similarities in representations then translate into similar behavior? If so, then how can a system's representations be modified to better match those of another system? These questions pertaining to the study of representational alignment are at the heart of some of the most promising research areas in contemporary cognitive science, neuroscience, and machine learning. In this Perspective, we survey the exciting recent developments in representational alignment research in the fields of cognitive science, neuroscience, and machine learning. Despite their overlapping interests, there is limited knowledge transfer between these fields, so work in one field ends up duplicated in another, and useful innovations are not shared effectively. To improve communication, we propose a unifying framework that can serve as a common language for research on representational alignment, and map several streams of existing work across fields within our framework. We also lay out open problems in representational alignment where progress can benefit all three of these fields. We hope that this paper will catalyze cross-disciplinary collaboration and accelerate progress for all communities studying and developing information processing systems.

Shachar Don-Yehiya, Ben Burtenshaw, Ramon Fernandez Astudillo et al. · huggingface, ibm-research

Human feedback on conversations with language language models (LLMs) is central to how these systems learn about the world, improve their capabilities, and are steered toward desirable and safe behaviors. However, this feedback is mostly collected by frontier AI labs and kept behind closed doors. In this work, we bring together interdisciplinary experts to assess the opportunities and challenges to realizing an open ecosystem of human feedback for AI. We first look for successful practices in peer production, open source, and citizen science communities. We then characterize the main challenges for open human feedback. For each, we survey current approaches and offer recommendations. We end by envisioning the components needed to underpin a sustainable and open human feedback ecosystem. In the center of this ecosystem are mutually beneficial feedback loops, between users and specialized models, incentivizing a diverse stakeholders community of model trainers and feedback providers to support a general open feedback pool.

Andi Peng, Aviv Netanyahu, Mark Ho et al.

Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness by making the model invariant to task-irrelevant changes in the agent's observation. However, designers don't know which concepts are irrelevant a priori, especially when different end users have different preferences about how the task is performed. We propose an interactive framework to leverage feedback directly from the user to identify personalized task-irrelevant concepts. Our key idea is to generate counterfactual demonstrations that allow users to quickly identify possible task-relevant and irrelevant concepts. The knowledge of task-irrelevant concepts is then used to perform data augmentation and thus obtain a policy adapted to personalized user objectives. We present experiments validating our framework on discrete and continuous control tasks with real human users. Our method (1) enables users to better understand agent failure, (2) reduces the number of demonstrations required for fine-tuning, and (3) aligns the agent to individual user task preferences.

Andi Peng, Mycal Tucker, Eoin Kenny et al. · mit

Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g., "bird" vs. "sparrow") and deploy the appropriate abstraction based on task. Inspired by this, we train neural models to generate a spectrum of discrete representations, and control the complexity of the representations (roughly, how many bits are allocated for encoding inputs) by tuning the entropy of the distribution over representations. In finetuning experiments, using only a small number of labeled examples for a new task, we show that (1) tuning the representation to a task-appropriate complexity level supports the highest finetuning performance, and (2) in a human-participant study, users were able to identify the appropriate complexity level for a downstream task using visualizations of discrete representations. Our results indicate a promising direction for rapid model finetuning by leveraging human insight.

Andreea Bobu, Andi Peng, Pulkit Agrawal et al.

To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior. However, if we want robots to act for and with people, their representations must not be just functional but also reflective of what humans care about, i.e. they must be aligned. We observe that current learning approaches suffer from representation misalignment, where the robot's learned representation does not capture the human's representation. We suggest that because humans are the ultimate evaluator of robot performance, we must explicitly focus our efforts on aligning learned representations with humans, in addition to learning the downstream task. We advocate that current representation learning approaches in robotics should be studied from the perspective of how well they accomplish the objective of representation alignment. We mathematically define the problem, identify its key desiderata, and situate current methods within this formalism. We conclude by suggesting future directions for exploring open challenges.

Andi Peng, Jessica Zosa Forde, Yonadav Shavit et al.

AI's rapid growth has been felt acutely by scholarly venues, leading to growing pains within the peer review process. These challenges largely center on the inability of specific subareas to identify and evaluate work that is appropriate according to criteria relevant to each subcommunity as determined by stakeholders of that subarea. We set forth a proposal that re-focuses efforts within these subcommunities through a decentralization of the reviewing and publication process. Through this re-centering effort, we hope to encourage each subarea to confront the issues specific to their process of academic publication and incentivization. This model has historically been successful for several subcommunities in AI, and we highlight those instances as examples for how the broader field can continue to evolve despite its continually growing size.

Andi Peng, Belinda Z. Li, Ilia Sucholutsky et al.

Many approaches to robot learning begin by inferring a reward function from a set of human demonstrations. To learn a good reward, it is necessary to determine which features of the environment are relevant before determining how these features should be used to compute reward. End-to-end methods for joint feature and reward learning (e.g., using deep networks or program synthesis techniques) often yield brittle reward functions that are sensitive to spurious state features. By contrast, humans can often generalizably learn from a small number of demonstrations by incorporating strong priors about what features of a demonstration are likely meaningful for a task of interest. How do we build robots that leverage this kind of background knowledge when learning from new demonstrations? This paper describes a method named ALGAE (Adaptive Language-Guided Abstraction from [Contrastive] Explanations) which alternates between using language models to iteratively identify human-meaningful features needed to explain demonstrated behavior, then standard inverse reinforcement learning techniques to assign weights to these features. Experiments across a variety of both simulated and real-world robot environments show that ALGAE learns generalizable reward functions defined on interpretable features using only small numbers of demonstrations. Importantly, ALGAE can recognize when features are missing, then extract and define those features without any human input -- making it possible to quickly and efficiently acquire rich representations of user behavior.

Christy Li, Sky CH-Wang, Andi Peng et al.

As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when prevention fails. We formalize a solution to this neglected challenge in post-execution safeguards as harm recovery: the problem of optimally steering an agent from a harmful state back to a safe one in alignment with human preferences. We ground preference-aligned recovery through a formative user study that identifies valued recovery dimensions and produces a natural language rubric. Our dataset of 1,150 pairwise judgments reveals context-dependent shifts in attribute importance, such as preferences for pragmatic, targeted strategies over comprehensive long-term approaches. We operationalize these learned insights in a reward model, re-ranking multiple candidate recovery plans generated by an agent scaffold at test time. To evaluate recovery capabilities systematically, we introduce BackBench, a benchmark of 50 computer-use tasks that test an agent's ability to recover from harmful states. Human evaluation shows our reward model scaffold yields higher-quality recovery trajectories than base agents and rubric-based scaffolds. Together, these contributions lay the foundation for a new class of agent safety methods -- ones that confront harm not only by preventing it, but by navigating its aftermath with alignment and intent.

Andreea Bobu, Andi Peng

As robots are increasingly deployed in real-world scenarios, a key question is how to best transfer knowledge learned in one environment to another, where shifting constraints and human preferences render adaptation challenging. A central challenge remains that often, it is difficult (perhaps even impossible) to capture the full complexity of the deployment environment, and therefore the desired tasks, at training time. Consequently, the representation, or abstraction, of the tasks the human hopes for the robot to perform in one environment may be misaligned with the representation of the tasks that the robot has learned in another. We postulate that because humans will be the ultimate evaluator of system success in the world, they are best suited to communicating the aspects of the tasks that matter to the robot. Our key insight is that effective learning from human input requires first explicitly learning good intermediate representations and then using those representations for solving downstream tasks. We highlight three areas where we can use this approach to build interactive systems and offer future directions of work to better create advanced collaborative robots.

Weihua Du, Qiushi Lyu, Jiaming Shan et al. · cmu

We introduce Constrained Human-AI Cooperation (CHAIC), an inclusive embodied social intelligence challenge designed to test social perception and cooperation in embodied agents. In CHAIC, the goal is for an embodied agent equipped with egocentric observations to assist a human who may be operating under physical constraints -- e.g., unable to reach high places or confined to a wheelchair -- in performing common household or outdoor tasks as efficiently as possible. To achieve this, a successful helper must: (1) infer the human's intents and constraints by following the human and observing their behaviors (social perception), and (2) make a cooperative plan tailored to the human partner to solve the task as quickly as possible, working together as a team (cooperative planning). To benchmark this challenge, we create four new agents with real physical constraints and eight long-horizon tasks featuring both indoor and outdoor scenes with various constraints, emergency events, and potential risks. We benchmark planning- and learning-based baselines on the challenge and introduce a new method that leverages large language models and behavior modeling. Empirical evaluations demonstrate the effectiveness of our benchmark in enabling systematic assessment of key aspects of machine social intelligence. Our benchmark and code are publicly available at https://github.com/UMass-Embodied-AGI/CHAIC.

Andi Peng, Ilia Sucholutsky, Belinda Z. Li et al.

We describe a framework for using natural language to design state abstractions for imitation learning. Generalizable policy learning in high-dimensional observation spaces is facilitated by well-designed state representations, which can surface important features of an environment and hide irrelevant ones. These state representations are typically manually specified, or derived from other labor-intensive labeling procedures. Our method, LGA (language-guided abstraction), uses a combination of natural language supervision and background knowledge from language models (LMs) to automatically build state representations tailored to unseen tasks. In LGA, a user first provides a (possibly incomplete) description of a target task in natural language; next, a pre-trained LM translates this task description into a state abstraction function that masks out irrelevant features; finally, an imitation policy is trained using a small number of demonstrations and LGA-generated abstract states. Experiments on simulated robotic tasks show that LGA yields state abstractions similar to those designed by humans, but in a fraction of the time, and that these abstractions improve generalization and robustness in the presence of spurious correlations and ambiguous specifications. We illustrate the utility of the learned abstractions on mobile manipulation tasks with a Spot robot.

Andi Peng, Andreea Bobu, Belinda Z. Li et al.

Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual representations containing task-relevant features, from language as a way to perform more generalizable learning. However, these abstractions also depend on a user's preference for what matters in a task, which may be hard to describe or infeasible to exhaustively specify using language alone. How do we construct abstractions to capture these latent preferences? We observe that how humans behave reveals how they see the world. Our key insight is that changes in human behavior inform us that there are differences in preferences for how humans see the world, i.e. their state abstractions. In this work, we propose using language models (LMs) to query for those preferences directly given knowledge that a change in behavior has occurred. In our framework, we use the LM in two ways: first, given a text description of the task and knowledge of behavioral change between states, we query the LM for possible hidden preferences; second, given the most likely preference, we query the LM to construct the state abstraction. In this framework, the LM is also able to ask the human directly when uncertain about its own estimate. We demonstrate our framework's ability to construct effective preference-conditioned abstractions in simulated experiments, a user study, as well as on a real Spot robot performing mobile manipulation tasks.

Andi Peng, Yuying Sun, Tianmin Shu et al.

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human communication, we study how to extract fine-grained data regarding why an example is preferred that is useful for learning more accurate reward models. We propose to enrich binary preference queries to ask both (1) which features of a given example are preferable in addition to (2) comparisons between examples themselves. We derive an approach for learning from these feature-level preferences, both for cases where users specify which features are reward-relevant, and when users do not. We evaluate our approach on linear bandit settings in both vision- and language-based domains. Results support the efficiency of our approach in quickly converging to accurate rewards with fewer comparisons vs. example-only labels. Finally, we validate the real-world applicability with a behavioral experiment on a mushroom foraging task. Our findings suggest that incorporating pragmatic feature preferences is a promising approach for more efficient user-aligned reward learning.

Jifan Zhang, Henry Sleight, Andi Peng et al.

Large language models (LLMs) are increasingly trained from AI constitutions and model specifications that establish behavioral guidelines and ethical principles. However, these specifications face critical challenges, including internal conflicts between principles and insufficient coverage of nuanced scenarios. We present a systematic methodology for stress-testing model character specifications, automatically identifying numerous cases of principle contradictions and interpretive ambiguities in current model specs. We stress test current model specs by generating scenarios that force explicit tradeoffs between competing value-based principles. Using a comprehensive taxonomy we generate diverse value tradeoff scenarios where models must choose between pairs of legitimate principles that cannot be simultaneously satisfied. We evaluate responses from twelve frontier LLMs across major providers (Anthropic, OpenAI, Google, xAI) and measure behavioral disagreement through value classification scores. Among these scenarios, we identify over 70,000 cases exhibiting significant behavioral divergence. Empirically, we show this high divergence in model behavior strongly predicts underlying problems in model specifications. Through qualitative analysis, we provide numerous example issues in current model specs such as direct contradiction and interpretive ambiguities of several principles. Additionally, our generated dataset also reveals both clear misalignment cases and false-positive refusals across all of the frontier models we study. Lastly, we also provide value prioritization patterns and differences of these models.

Shannon Zejiang Shen, Valerie Chen, Ken Gu et al. · cmu

Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We argue for a shift from building and assessing task completion agents to developing collaborative agents, assessed not only by the quality of their final outputs but by how well they engage with and enhance human effort throughout the problem-solving process. To support this shift, we introduce collaborative effort scaling, a framework that captures how an agent's utility grows with increasing user involvement. Through case studies and simulated evaluations, we show that state-of-the-art agents often underperform in multi-turn, real-world scenarios, revealing a missing ingredient in agent design: the ability to sustain engagement and scaffold user understanding. Collaborative effort scaling offers a lens for diagnosing agent behavior and guiding development toward more effective interactions.

Andi Peng, Besmira Nushi, Emre Kiciman et al.

In AI-assisted decision-making, effective hybrid (human-AI) teamwork is not solely dependent on AI performance alone, but also on its impact on human decision-making. While prior work studies the effects of model accuracy on humans, we endeavour here to investigate the complex dynamics of how both a model's predictive performance and bias may transfer to humans in a recommendation-aided decision task. We consider the domain of ML-assisted hiring, where humans -- operating in a constrained selection setting -- can choose whether they wish to utilize a trained model's inferences to help select candidates from written biographies. We conduct a large-scale user study leveraging a re-created dataset of real bios from prior work, where humans predict the ground truth occupation of given candidates with and without the help of three different NLP classifiers (random, bag-of-words, and deep neural network). Our results demonstrate that while high-performance models significantly improve human performance in a hybrid setting, some models mitigate hybrid bias while others accentuate it. We examine these findings through the lens of decision conformity and observe that our model architecture choices have an impact on human-AI conformity and bias, motivating the explicit need to assess these complex dynamics prior to deployment.

Andi Peng, Besmira Nushi, Emre Kiciman et al.

Although systematic biases in decision-making are widely documented, the ways in which they emerge from different sources is less understood. We present a controlled experimental platform to study gender bias in hiring by decoupling the effect of world distribution (the gender breakdown of candidates in a specific profession) from bias in human decision-making. We explore the effectiveness of \textit{representation criteria}, fixed proportional display of candidates, as an intervention strategy for mitigation of gender bias by conducting experiments measuring human decision-makers' rankings for who they would recommend as potential hires. Experiments across professions with varying gender proportions show that balancing gender representation in candidate slates can correct biases for some professions where the world distribution is skewed, although doing so has no impact on other professions where human persistent preferences are at play. We show that the gender of the decision-maker, complexity of the decision-making task and over- and under-representation of genders in the candidate slate can all impact the final decision. By decoupling sources of bias, we can better isolate strategies for bias mitigation in human-in-the-loop systems.

Caleb Robinson, Anthony Ortiz, Kolya Malkin et al.

We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data to label, and see the resulting effect on the model's predictions. This bi-directional feedback loop allows humans to learn how the model responds to new data. Our hypothesis is that this rich feedback allows human labelers to create mental models that enable them to better choose which biases to introduce to the model. We compare human-selected points to points selected using standard active learning methods. We further investigate how the fine-tuning methodology impacts the human labelers' performance. We implement this framework for fine-tuning high-resolution land cover segmentation models. Specifically, we fine-tune a deep neural network -- trained to segment high-resolution aerial imagery into different land cover classes in Maryland, USA -- to a new spatial area in New York, USA. The tight loop turns the algorithm and the human operator into a hybrid system that can produce land cover maps of a large area much more efficiently than the traditional workflows. Our framework has applications in geospatial machine learning settings where there is a practically limitless supply of unlabeled data, of which only a small fraction can feasibly be labeled through human efforts.