arXiv subjects

Anca Dragan

Publications and source records attributed to Anca Dragan.

At least 19 recordsLinked to original sources

arXiv2026

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether LLM monitoring pipelines can detect these OOD alignment failures by introducing a benchmark called Misalignment Out Of Distribution (MOOD). It is difficult to find failures that are truly OOD for off-the-shelf models trained on vast safety datasets. We sidestep this by including a restricted training set in MOOD that we use to train our own monitors, as well as seven test sets with diverse alignment failures that are outside the training distribution. Using MOOD, we find that guard models (safety classifiers) often fail to generalize OOD. To fix this, we propose combining guard models with OOD detectors. We test four types of OOD detectors and find that a combination of a guard model with Mahalanobis distance and perplexity-based OOD detectors can improve recall from 39% to 45%. We also establish positive scaling trends across model scales for monitors that combine a guard model and OOD detector; we find that incorporating OOD detection into monitoring achieves a higher recall gain than using a guard model with 20 times more parameters. Our work suggests that OOD detection should be a crucial component of LLM monitoring and provides a foundation for further work on this important problem. We release the code and data for our experiments publicly, and you can find the relevant links here: https://github.com/Dylan102938/mood-bench.

cs.AI↗

arXiv2026

Can AI mediation improve democratic deliberation?

The strength of democracy lies in the free and equal exchange of diverse viewpoints. Living up to this ideal at scale faces inherent tensions: broad participation, meaningful deliberation, and political equality often trade off with one another (Fishkin, 2011). We ask whether and how artificial intelligence (AI) could help navigate this "trilemma" by engaging with a recent example of a large language model (LLM)-based system designed to help people with diverse viewpoints find common ground (Tessler, Bakker, et al., 2024). Here, we explore the implications of the introduction of LLMs into deliberation augmentation tools, examining their potential to enhance participation through scalability, improve political equality via fair mediation, and foster meaningful deliberation by, for example, surfacing trustworthy information. We also point to key challenges that remain. Ultimately, a range of empirical, technical, and theoretical advancements are needed to fully realize the promise of AI-mediated deliberation for enhancing citizen engagement and strengthening democratic deliberation.

cs.CY↗

arXiv2025

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

We introduce The FACTS Leaderboard, an online leaderboard suite and associated set of benchmarks that comprehensively evaluates the ability of language models to generate factually accurate text across diverse scenarios. The suite provides a holistic measure of factuality by aggregating the performance of models on four distinct sub-leaderboards: (1) FACTS Multimodal, which measures the factuality of responses to image-based questions; (2) FACTS Parametric, which assesses models' world knowledge by answering closed-book factoid questions from internal parameters; (3) FACTS Search, which evaluates factuality in information-seeking scenarios, where the model must use a search API; and (4) FACTS Grounding (v2), which evaluates whether long-form responses are grounded in provided documents, featuring significantly improved judge models. Each sub-leaderboard employs automated judge models to score model responses, and the final suite score is an average of the four components, designed to provide a robust and balanced assessment of a model's overall factuality. The FACTS Leaderboard Suite will be actively maintained, containing both public and private splits to allow for external participation while guarding its integrity. It can be found at https://www.kaggle.com/benchmarks/google/facts .

cs.CL↗

arXiv2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

cs.AI↗

arXiv2025

Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning (RL) fine-tuning can enable such planning in principle, but suffers from drawbacks that hinder scalability. In particular, multi-turn RL training incurs high memory and computational costs, which are exacerbated when training LLMs as policies. Furthermore, the largest LLMs do not expose the APIs necessary to be trained in such manner. As a result, modern methods to improve the reasoning of LLMs rely on sophisticated prompting mechanisms rather than RL fine-tuning. To remedy this, we propose a novel approach that uses goal-conditioned value functions to guide the reasoning of LLM agents, that scales even to large API-based models. These value functions predict how a task will unfold given an action, allowing the LLM agent to evaluate multiple possible outcomes, both positive and negative, to plan effectively. In addition, these value functions are trained over reasoning steps rather than full actions, to be a concise and light-weight module that facilitates decision-making in multi-turn interactions. We validate our method on tasks requiring interaction, including tool use, social deduction, and dialogue, demonstrating superior performance over both RL fine-tuning and prompting methods while maintaining efficiency and scalability.

cs.CL↗

arXiv2025

Training LLM Agents to Empower Humans

Assistive agents should not only take actions on behalf of a human, but also step out of the way and cede control when there are important decisions to be made. However, current methods for building assistive agents, whether via mimicking expert humans or via RL finetuning on an inferred reward, often encourage agents to complete tasks on their own rather than truly assisting the human attain their objectives. Additionally, these methods often require costly explicit human feedback to provide a training signal. We propose a new approach to tuning assistive language models based on maximizing the human's empowerment, their ability to effect desired changes in the environment. Our empowerment-maximizing method, Empower, only requires offline text data, providing a self-supervised method for fine-tuning language models to better assist humans. To study the efficacy of our approach, we conducted an 18-person user study comparing our empowerment assistant with a strong baseline. Participants preferred our assistant 78% of the time (p=0.015), with a 31% higher acceptance rate and 38% fewer suggestions. Additionally, we introduce a new environment for evaluating multi-turn code assistance using simulated humans. Using this environment, we show that agents trained with Empower increase the success rate of a simulated human programmer on challenging coding questions by an average of 192% over an SFT baseline. With this empowerment objective, we provide a framework for useful aligned AI agents at scale using only offline data without the need for any additional human feedback or verifiable rewards.

cs.AI↗

arXiv2025

CTRL-Rec: Controlling Recommender Systems With Natural Language

When users are dissatisfied with recommendations from a recommender system, they often lack fine-grained controls for changing them. Large language models (LLMs) offer a solution by allowing users to guide their recommendations through natural language requests (e.g., "I want to see respectful posts with a different perspective than mine"). We propose a method, CTRL-Rec, that allows for natural language control of traditional recommender systems in real-time with computational efficiency. Specifically, at training time, we use an LLM to simulate whether users would approve of items based on their language requests, and we train embedding models that approximate such simulated judgments. We then integrate these user-request-based predictions into the standard weighting of signals that traditional recommender systems optimize. At deployment time, we require only a single LLM embedding computation per user request, allowing for real-time control of recommendations. In experiments with the MovieLens dataset, our method consistently allows for fine-grained control across a diversity of requests. In a study with 19 Letterboxd users, we find that CTRL-Rec was positively received by users and significantly enhanced users' sense of control and satisfaction with recommendations compared to traditional controls.

cs.AI↗

arXiv2025

AssistanceZero: Scalably Solving Assistance Games

Assistance games are a promising alternative to reinforcement learning from human feedback (RLHF) for training AI assistants. Assistance games resolve key drawbacks of RLHF, such as incentives for deceptive behavior, by explicitly modeling the interaction between assistant and user as a two-player game where the assistant cannot observe their shared goal. Despite their potential, assistance games have only been explored in simple settings. Scaling them to more complex environments is difficult because it requires both solving intractable decision-making problems under uncertainty and accurately modeling human users' behavior. We present the first scalable approach to solving assistance games and apply it to a new, challenging Minecraft-based assistance game with over $10^{400}$ possible goals. Our approach, AssistanceZero, extends AlphaZero with a neural network that predicts human actions and rewards, enabling it to plan under uncertainty. We show that AssistanceZero outperforms model-free RL algorithms and imitation learning in the Minecraft-based assistance game. In a human study, our AssistanceZero-trained assistant significantly reduces the number of actions participants take to complete building tasks in Minecraft. Our results suggest that assistance games are a tractable framework for training effective AI assistants in complex environments. Our code and models are available at https://github.com/cassidylaidlaw/minecraft-building-assistance-game.

cs.AI↗

arXiv2025

An Approach to Technical AGI Safety and Security

Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough to significantly harm humanity. We identify four areas of risk: misuse, misalignment, mistakes, and structural risks. Of these, we focus on technical approaches to misuse and misalignment. For misuse, our strategy aims to prevent threat actors from accessing dangerous capabilities, by proactively identifying dangerous capabilities, and implementing robust security, access restrictions, monitoring, and model safety mitigations. To address misalignment, we outline two lines of defense. First, model-level mitigations such as amplified oversight and robust training can help to build an aligned model. Second, system-level security measures such as monitoring and access control can mitigate harm even if the model is misaligned. Techniques from interpretability, uncertainty estimation, and safer design patterns can enhance the effectiveness of these mitigations. Finally, we briefly outline how these ingredients could be combined to produce safety cases for AGI systems.

cs.AI↗

arXiv2025

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

Because it is difficult to precisely specify complex objectives, reinforcement learning policies are often optimized using proxy reward functions that only approximate the true goal. However, optimizing proxy rewards frequently leads to reward hacking: the optimized reward function ceases to be a good proxy and the resulting policy performs poorly with respect to the unspecified true reward. Principled solutions to reward hacking have been impeded by the lack of a good definition for the problem. To address this gap, we introduce a definition of reward hacking based on the correlation between proxy and true rewards for states and actions seen by a "reference policy" that breaks down under optimization. We show that this definition captures reward hacking behavior across several realistic settings, including in reinforcement learning from human feedback (RLHF). Using our formulation, we show theoretically that regularization to the reference policy can effectively prevent reward hacking. While the current practice in RLHF applies a KL penalty between action distributions for this purpose, our theory suggests regularizing the $χ^2$ divergence between the policies' occupancy measures can be more effective. We intuitively show the benefits of this type of regularization and demonstrate that it better mitigates reward hacking in practice across four realistic settings, including RLHF. Our code is available at https://github.com/cassidylaidlaw/orpo.

cs.LG↗

arXiv2025

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor features learned by contrastive learning (after a change of variables) form a temporal distance that does satisfy the triangle inequality, even in stochastic settings. Importantly, this temporal distance is computationally efficient to estimate, even in high-dimensional and stochastic settings. Experiments in controlled settings and benchmark suites demonstrate that an RL algorithm based on these new temporal distances exhibits combinatorial generalization (i.e., "stitching") and can sometimes learn more quickly than prior methods, including those based on quasimetrics.

cs.LG↗

arXiv2025

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

As LLMs become more widely deployed, there is increasing interest in directly optimizing for feedback from end users (e.g. thumbs up) in addition to feedback from paid annotators. However, training to maximize human feedback creates a perverse incentive structure for the AI to resort to manipulative or deceptive tactics to obtain positive feedback from users who are vulnerable to such strategies. We study this phenomenon by training LLMs with Reinforcement Learning with simulated user feedback in environments of practical LLM usage. In our settings, we find that: 1) Extreme forms of "feedback gaming" such as manipulation and deception are learned reliably; 2) Even if only 2% of users are vulnerable to manipulative strategies, LLMs learn to identify and target them while behaving appropriately with other users, making such behaviors harder to detect; 3) To mitigate this issue, it may seem promising to leverage continued safety training or LLM-as-judges during training to filter problematic outputs. Instead, we found that while such approaches help in some of our settings, they backfire in others, sometimes even leading to subtler manipulative behaviors. We hope our results can serve as a case study which highlights the risks of using gameable feedback sources -- such as user feedback -- as a target for RL.

cs.LG↗

arXiv2025

Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following

Effective task representations should facilitate compositionality, such that after learning a variety of basic tasks, an agent can perform compound tasks consisting of multiple steps simply by composing the representations of the constituent steps together. While this is conceptually simple and appealing, it is not clear how to automatically learn representations that enable this sort of compositionality. We show that learning to associate the representations of current and future states with a temporal alignment loss can improve compositional generalization, even in the absence of any explicit subtask planning or reinforcement learning. We evaluate our approach across diverse robotic manipulation tasks as well as in simulation, showing substantial improvements for tasks specified with either language or goal images.

cs.RO↗

arXiv2025

Context Steering: Controllable Personalization at Inference Time

To deliver high-quality, personalized responses, large language models (LLMs) must effectively incorporate context -- personal, demographic, and cultural information specific to an end-user. For example, asking the model to explain Newton's second law with the context "I am a toddler" should produce a response different from when the context is "I am a physics professor". However, leveraging the context in practice is a nuanced and challenging task, and is often dependent on the specific situation or user base. The model must strike a balance between providing specific, personalized responses and maintaining general applicability. Current solutions, such as prompt-engineering and fine-tuning, require collection of contextually appropriate responses as examples, making them time-consuming and less flexible to use across different contexts. In this work, we introduce Context Steering (CoS) -- a simple, training-free decoding approach that amplifies the influence of the context in next token predictions. CoS computes contextual influence by comparing the output probabilities from two LLM forward passes: one that includes the context and one that does not. By linearly scaling the contextual influence, CoS allows practitioners to flexibly control the degree of personalization for different use cases. We show that CoS can be applied to autoregressive LLMs, and demonstrates strong performance in personalized recommendations. Additionally, we show that CoS can function as a Bayesian Generative model to infer and quantify correlations between open-ended texts, broadening its potential applications.

cs.CL↗

arXiv2025

Learning to Assist Humans without Inferring Rewards

Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects actions to help the human reach that goal. This approach requires inferring intentions, which can be difficult in high-dimensional settings. We build upon prior work that studies assistance through the lens of empowerment: an assistive agent aims to maximize the influence of the human's actions such that they exert a greater control over the environmental outcomes and can solve tasks in fewer steps. We lift the major limitation of prior work in this area--scalability to high-dimensional settings--with contrastive successor representations. We formally prove that these representations estimate a similar notion of empowerment to that studied by prior work and provide a ready-made mechanism for optimizing it. Empirically, our proposed method outperforms prior methods on synthetic benchmarks, and scales to Overcooked, a cooperative game setting. Theoretically, our work connects ideas from information theory, neuroscience, and reinforcement learning, and charts a path for representations to play a critical role in solving assistive problems.

cs.AI↗

arXiv2024

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

Value-based reinforcement learning (RL) can in principle learn effective policies for a wide range of multi-turn problems, from games to dialogue to robotic control, including via offline RL from static previously collected datasets. However, despite the widespread use of policy gradient methods to train large language models for single turn tasks (e.g., question answering), value-based methods for multi-turn RL in an off-policy or offline setting have proven particularly challenging to scale to the setting of large language models. This setting requires effectively leveraging pretraining, scaling to large architectures with billions of parameters, and training on large datasets, all of which represent major challenges for current value-based RL methods. In this work, we propose a novel offline RL algorithm that addresses these drawbacks, casting Q-learning as a modified supervised fine-tuning (SFT) problem where the probabilities of tokens directly translate to Q-values. In this way we obtain an algorithm that smoothly transitions from maximizing the likelihood of the data during pretraining to learning a near-optimal Q-function during finetuning. Our algorithm has strong theoretical foundations, enjoying performance bounds similar to state-of-the-art Q-learning methods, while in practice utilizing an objective that closely resembles SFT. Because of this, our approach can enjoy the full benefits of the pretraining of language models, without the need to reinitialize any weights before RL finetuning, and without the need to initialize new heads for predicting values or advantages. Empirically, we evaluate our method on both pretrained LLMs and VLMs, on a variety of tasks including both natural language dialogue and robotic manipulation and navigation from images.

cs.LG↗

arXiv2024

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback

Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on partial observations? We formally define two failure cases: deceptive inflation and overjustification. Modeling the human as Boltzmann-rational w.r.t. a belief over trajectories, we prove conditions under which RLHF is guaranteed to result in policies that deceptively inflate their performance, overjustify their behavior to make an impression, or both. Under the new assumption that the human's partial observability is known and accounted for, we then analyze how much information the feedback process provides about the return function. We show that sometimes, the human's feedback determines the return function uniquely up to an additive constant, but in other realistic cases, there is irreducible ambiguity. We propose exploratory research directions to help tackle these challenges, experimentally validate both the theoretical concerns and potential mitigations, and caution against blindly applying RLHF in partially observable settings.

cs.LG↗

arXiv2024

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations

Recent progress on large language models (LLMs) has enabled dialogue agents to generate highly naturalistic and plausible text. However, current LLM language generation focuses on responding accurately to questions and requests with a single effective response. In reality, many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion. Accounting for how an agent can effectively steer a conversation is a crucial ability in many dialogue tasks, from healthcare to preference elicitation. Existing methods for fine-tuning dialogue agents to accomplish such tasks would rely on curating some amount of expert data. However, doing so often requires understanding the underlying cognitive processes of the conversational partner, which is a skill neither humans nor LLMs trained on human data can reliably do. Our key insight is that while LLMs may not be adept at identifying effective strategies for steering conversations a priori, or in the middle of an ongoing conversation, they can do so post-hoc, or in hindsight, after seeing how their conversational partner responds. We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations. We apply our approach to two domains that require understanding human mental state, intelligent interaction, and persuasion: mental health support, and soliciting charitable donations. Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.

cs.LG↗