Development of dexterous manipulation hardware has primarily focused on hands and grippers. However, robotic wrists are equally critical, often playing a greater role than the end effector itself. Many conventional wrist designs fall short in human environments because they are too large or rely on rigid, high-reduction actuators that cannot support dynamic, contact-rich tasks. Some designs address these issues using backdrivable quasi-direct drive (QDD) actuators and compact form factors. However, they are often difficult to model and control due to coupled kinematics or high mechanical inertia. We present DexWrist, a robotic wrist that is designed to advance robotic manipulation in highly constrained environments, enable dynamic and contact-rich tasks, and simplify policy learning. DexWrist provides low-impedance actuation, low inertia, integrated proprioception, high speed, and a large workspace. Together, these capabilities support robust learning-based manipulation. DexWrist accelerates policy learning by: (i) enabling faster teleoperation for scalable data collection, (ii) simplifying the learned function through shorter trajectories and decoupled degrees of freedom (DOFs), (iii) providing natural backdrivability for safe contact without complex compliant controllers, and (iv) expanding the manipulation workspace in cluttered scenes. In our experiments, DexWrist improved policy success rates by 50-55% and reduced task completion times by a factor of 3-5. More details about the wrist can be found at https://dexwrist.csail.mit.edu.

We use the notion of oracle machines and reductions from computability theory to formalise different Human-in-the-loop (HITL) setups for AI systems, distinguishing between trivial human monitoring (i.e., total functions), single endpoint human action (i.e., many-one reductions), and highly involved human-AI interaction (i.e., Turing reductions). We then proceed to show that the legal status and safety of different setups vary greatly. We present a taxonomy to categorise HITL failure modes, highlighting the practical limitations of HITL setups. We then identify omissions in UK and EU legal frameworks, which focus on HITL setups that may not always achieve the desired ethical, legal, and sociotechnical outcomes. We suggest areas where the law should recognise the effectiveness of different HITL setups and assign responsibility in these contexts, avoiding human "scapegoating". Our work shows an unavoidable trade-off between attribution of legal responsibility, and technical explainability. Overall, we show how HITL setups involve many technical design decisions, and can be prone to failures out of the humans' control. Our formalisation and taxonomy opens up a new analytic perspective on the challenges in creating HITL setups, helping inform AI developers and lawmakers on designing HITL setups to better achieve their desired outcomes.

Large Language Models (LLMs) not only have solved complex reasoning problems but also exhibit remarkable performance in tasks that require subjective decision making. Existing studies suggest that LLM generations can be subjectively grounded to some extent, yet exploring whether LLMs can account for individual-level subjectivity has not been sufficiently studied. In this paper, we characterize subjectivity of individuals on social media and infer their moral judgments using LLMs. We propose a framework, SOLAR (Subjective Ground with Value Abstraction), that observes value conflicts and trade-offs in the user-generated texts to better represent subjective ground of individuals. Empirical results show that our framework improves overall inference results as well as performance on controversial situations. Additionally, we qualitatively show that SOLAR provides explanations about individuals' value preferences, which can further account for their judgments.

Decentralized Autonomous Organizations (DAOs) use smart contracts to foster communities working toward common goals. Existing definitions of decentralization, however -- the 'D' in DAO -- fall short of capturing the key properties characteristic of diverse and equitable participation. This work proposes a new framework for measuring DAO decentralization called Voting-Bloc Entropy (VBE, pronounced ''vibe''). VBE is based on the idea that voters with closely aligned interests act as a centralizing force and should be modeled as such. VBE formalizes this notion by measuring the similarity of participants' utility functions across a set of voting rounds. Unlike prior, ad hoc definitions of decentralization, VBE derives from first principles: We introduce a simple (yet powerful) reinforcement learning-based conceptual model for voting, that in turn implies VBE. We first show VBE's utility as a theoretical tool. We prove a number of results about the (de)centralizing effects of vote delegation, proposal bundling, bribery, etc. that are overlooked in previous notions of DAO decentralization. Our results lead to practical suggestions for enhancing DAO decentralization. We also show how VBE can be used empirically by presenting measurement studies and VBE-based governance experiments. We make the tools we developed for these results available to the community in the form of open-source artifacts in order to facilitate future study of DAO decentralization.

Asynchronous patient-clinician messaging via EHR portals is a growing source of clinician workload, prompting interest in large language models (LLMs) to assist with draft responses. However, LLM outputs may contain clinical inaccuracies, omissions, or tone mismatches, making robust evaluation essential. Our contributions are threefold: (1) we introduce a clinically grounded error ontology comprising 5 domains and 59 granular error codes, developed through inductive coding and expert adjudication; (2) we develop a retrieval-augmented evaluation pipeline (RAEC) that leverages semantically similar historical message-response pairs to improve judgment quality; and (3) we provide a two-stage prompting architecture using DSPy to enable scalable, interpretable, and hierarchical error detection. Our approach assesses the quality of drafts both in isolation and with reference to similar past message-response pairs retrieved from institutional archives. Using a two-stage DSPy pipeline, we compared baseline and reference-enhanced evaluations on over 1,500 patient messages. Retrieval context improved error identification in domains such as clinical completeness and workflow appropriateness. Human validation on 100 messages demonstrated superior agreement (concordance = 50% vs. 33%) and performance (F1 = 0.500 vs. 0.256) of context-enhanced labels vs. baseline, supporting the use of our RAEC pipeline as AI guardrails for patient messaging.

Mutual understanding of artificial agents' decisions is key to ensuring a trustworthy and successful human-robot interaction. Hence, robots are expected to make reasonable decisions and communicate them to humans when needed. In this article, the focus is on an approach to modeling and reasoning about the comparison of two competing plans, so that robots can later explain the divergent result. First, a novel ontological model is proposed to formalize and reason about the differences between competing plans, enabling the classification of the most appropriate one (e.g., the shortest, the safest, the closest to human preferences, etc.). This work also investigates the limitations of a baseline algorithm for ontology-based explanatory narration. To address these limitations, a novel algorithm is presented, leveraging divergent knowledge between plans and facilitating the construction of contrastive narratives. Through empirical evaluation, it is observed that the explanations excel beyond the baseline method.

Large language models deployed in sensitive applications increasingly require the ability to unlearn specific knowledge, such as user requests, copyrighted materials, or outdated information, without retraining from scratch to ensure regulatory compliance, user privacy, and safety. This task, known as machine unlearning, aims to remove the influence of targeted data (forgetting) while maintaining performance on the remaining data (retention). A common approach is to formulate this as a multi-objective problem and reduce it to a single-objective problem via scalarization, where forgetting and retention losses are combined using a weighted sum. However, this often results in unstable training dynamics and degraded model utility due to conflicting gradient directions. To address these challenges, we propose OFMU, a penalty-based bi-level optimization framework that explicitly prioritizes forgetting while preserving retention through a hierarchical structure. Our method enforces forgetting via an inner maximization step that incorporates a similarity-aware penalty to decorrelate the gradients of the forget and retention objectives, and restores utility through an outer minimization step. To ensure scalability, we develop a two-loop algorithm with provable convergence guarantees under both convex and non-convex regimes. We further provide a rigorous theoretical analysis of convergence rates and show that our approach achieves better trade-offs between forgetting efficacy and model utility compared to prior methods. Extensive experiments across vision and language benchmarks demonstrate that OFMU consistently outperforms existing unlearning methods in both forgetting efficacy and retained utility.

Large language models (LLMs) often respond confidently to questions even when they lack the necessary information, leading to hallucinated answers. In this work, we study the problem of (un)answerability detection, focusing on extractive question answering (QA) where the model should determine if a passage contains sufficient information to answer a given question. We propose a simple approach for identifying a direction in the model's activation space that captures unanswerability and uses it for classification. This direction is selected by applying activation additions during inference and measuring their impact on the model's abstention behavior. We show that projecting hidden activations onto this direction yields a reliable score for (un)answerability classification. Experiments on two open-weight LLMs and four extractive QA benchmarks show that our method effectively detects unanswerable questions and generalizes better across datasets than existing prompt-based and classifier-based approaches. Moreover, the obtained directions extend beyond extractive QA to unanswerability that stems from factors, such as lack of scientific consensus and subjectivity. Last, causal interventions show that adding or ablating the directions effectively controls the abstention behavior of the model.

Large language models (LLMs) are known to generate politically biased text, yet how such biases arise remains unclear. A crucial step toward answering this question is the analysis of training data, whose political content remains largely underexplored in current LLM research. To address this gap, we present in this paper an analysis of the pre- and post-training corpora of OLMO2, the largest fully open-source model released together with its complete dataset. From these corpora, we draw large random samples, automatically annotate documents for political orientation, and analyze their source domains and content. We then assess how political content in the training data correlates with models' stance on specific policy issues. Our analysis shows that left-leaning documents predominate across datasets, with pre-training corpora containing significantly more politically engaged content than post-training data. We also find that left- and right-leaning documents frame similar topics through distinct values and sources of legitimacy. Finally, the predominant stance in the training data strongly correlates with models' political biases when evaluated on policy issues. These findings underscore the need to integrate political content analysis into future data curation pipelines as well as in-depth documentation of filtering strategies for transparency.

Large language models (LLMs) excel at operating at scale by leveraging social media and various data crawled from the web. Whereas existing corpora are diverse, their frequent lack of long-term temporal structure may however limit an LLM's ability to contextualize semantic and normative evolution of language and to capture diachronic variation. To support analysis and training for the latter, we introduce CHRONOBERG, a temporally structured corpus of English book texts spanning 250 years, curated from Project Gutenberg and enriched with a variety of temporal annotations. First, the edited nature of books enables us to quantify lexical semantic change through time-sensitive Valence-Arousal-Dominance (VAD) analysis and to construct historically calibrated affective lexicons to support temporally grounded interpretation. With the lexicons at hand, we demonstrate a need for modern LLM-based tools to better situate their detection of discriminatory language and contextualization of sentiment across various time-periods. In fact, we show how language models trained sequentially on CHRONOBERG struggle to encode diachronic shifts in meaning, emphasizing the need for temporally aware training and evaluation pipelines, and positioning CHRONOBERG as a scalable resource for the study of linguistic change and temporal generalization. Disclaimer: This paper includes language and display of samples that could be offensive to readers. Open Access: Chronoberg is available publicly on HuggingFace at ( https://huggingface.co/datasets/spaul25/Chronoberg). Code is available at (https://github.com/paulsubarna/Chronoberg).