Searcharxiv⌕ Search

arXiv subjects

Alexander Spangher

Publications and source records attributed to Alexander Spangher.

At least 19 recordsLinked to original sources

DOCKET: A Pluralistic Benchmark for Evaluating AI-Assisted Policy Feedback in U.S. Rulemaking

As AI models advance and impact deliberative democracies, there is a growing need to assess their support of pluralistic viewpoints. Most pluralism benchmarks are insufficient for this: they are not grounded in diversity (i.e., stakeholders across different frames, skills and needs), quality (i.e., rigorous and technical debates), and impact (i.e., invested deliberators and real-world outcomes). To address this, we first (i) curate DOCKET, the most comprehensive dataset of the U.S. Federal Notice & Comment process to date. DOCKET consists of 42.3M public comments on 22,400 regulations across 44 government agencies between 2016 and 2026 and contains millions of policy debates; we link public comments to particular policy items proposed by regulators to track the public's attention and the responsiveness of regulators to public input. (ii) Next, we demonstrate the pluralistic utility of DOCKET - we show that public commenters have a wide breadth of perspectives with significant depth in policy expertise and that regulators are often responsive. (iii) Finally, we present DOCKETBench, the first systematic evaluation of LLMs' ability to represent human policy perspectives in federal rulemaking. Only 18-30% of LLM-generated feedback aligns with real human comments. LLMs critique proposals broadly but generally, lacking the specific grounding, citations, and lived-experience arguments that humans bring to bear; in addition, most models we test systematically agree with government perspectives (overlapping with up to 68% of their claims) and agree least with labor unions (as little as 26% of their claims), demonstrating a fundamental skew in perspectives that even tools like persona modeling do not solve. Taken together, we reveal fundamental gaps in how language models navigate real policy issues, and DOCKETBench serves as a testbed for closing those gaps in a crucial real-world domain.

cs.CY↗

Articulation Upper Bounds for Language Models

Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language? We take steps towards measuring this in LLMs as follows: for a set of concepts, we measure how well each concept can be transmitted between two LLMs as their capabilities scale. This requires novel measurement tools: (1) optimal messages: we introduce a prompt optimization algorithm that beats existing algorithms by up to 14% on benchmarks and accurately estimates prompt upper bounds. (2) A transmission measure: the sender is asked to label text; the receiver then tries to recover the sender's prompt, and recovery is measured; we find this correlates strongly with human label error. With these measures, we use observational scaling laws to study how transmissibility of a concept, conveyed with optimal messages, increases as transmitter and receiver capacity grows: does it asymptote below or above a threshold? Measuring 1.2k concepts in eight domains, we find concepts that (a) can be fully articulated; these concepts usually depend on local patterns, e.g. "joke ends with surprise"; (b) might be articulated by future, stronger models; these rely on whole-text structural patterns, e.g. "story's worldbuilding coherence"; (c) concepts that face articulability limits; these concepts' meaning, we find, is tied to identity and social-group awareness, e.g. "comic voice". Interesting, these same concepts are not all challenging for humans: humans have moderate-to-high levels of agreement in 76% of concepts that LLMs struggle with; articulation limits, we find, are executor relative. Finally, we characterize the nature of improvement in each case: while recoverable concepts can be articulated through definitions and explanations, irrecoverable concepts cannot be transmitted, even with examples, and might require novel learning mechanisms.

cs.AI↗

Verifiable, Articulable, and Tacit Components of Preference

What makes a short story gripping; a news article newsworthy; or a math proof elegant? These constructs resist articulation or verification; their meaning is at least partially tacit. However, modern AI models are improved primarily via articulated constitutions, rubrics and verifiers (i.e. in RLAIF and RLVR); tacit components of preferences are typically understudied. We introduce a large, labeled preference dataset CreativePreferences, containing 2.8M texts labeled by 317M human preference judgments across 7 creative domains, with 42 benchmark tasks. We model these labels with executable programs, rubric banks and densely trained models (V, A and VAT, respectively). We observe robust articulability gaps, VAT-VA; and verifiability gaps, VAT-V; we estimate upper and lower bounds for each gap with a novel measurement approach that discovers articulable and verifiable metrics, identifies spurious variables and estimates the value of undiscovered metrics using capture-recapture. These gaps occur across all domains, even in domains traditionally treated as fully verifiable: correctness-centered domains (i.e. mathematics and software engineering) and claim- and novelty-centric domains (i.e. news, patents, peer review). The size of the gap varies based on domain (e.g. peer review and creative writing have the largest articulability gaps) and widens as more people take part in the judgment, consistent with Collins' collective tacit knowledge. We show two consequences: (1) on human generations, the full model more closely matches human preferences, often in disagreement with articulated criteria, and (2) in an analogy to Goodhart's law, articulating preference shifts it away from the tacit dimension. Articulability and verifiability gaps are consequential; we give recommendations on when tasks can be prompted; how learning mechanisms might improve; and when to leave judgments with humans.

cs.AI↗

Human-AI Co-Creativity: Advances, Opportunities, and Challenges

This survey article has grown out of the human-AI co-creativity workshop organized by the authors at the ICML 2026 conference. We organized this workshop as part of a community-building effort to bring together researchers and practitioners interested in topics of generative AI, creativity, and human-AI co-creation. This article aims to provide an overview of the workshop activities and highlight several future research directions in the area of human-AI co-creativity.

cs.CY↗

Evaluating Commercial AI Chatbots as News Intermediaries

AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their proprietary search integrations and retrieval-synthesis pipelines, handle emerging facts across languages and regions. We present a 14-day (February 9-22, 2026) evaluation of six AI chatbots (Gemini 3 Flash and Pro, Grok 4, Claude 4.5 Sonnet, GPT-5 and GPT-4o mini) on 2,100 factual questions derived from same-day BBC News reporting across six regional services (US & Canada, Arabic, Afrique, Hindi, Russian, Turkish). The best systems achieve over 90% multiple-choice accuracy on questions about events reported hours earlier. The same systems, however, lose 11-13% under free-response evaluation, and 16-17% across the cohort. We further characterize three failure patterns. First, every model achieves its lowest accuracy on Hindi (79% vs. 89-91% elsewhere) and citations indicate an Anglophone retrieval bias (e.g., models answering Hindi queries cite English Wikipedia more than any Hindi outlet). Second, retrieval, not reasoning, failures drive over 70% of all errors. When models retrieve a correct source, they often extract the correct answer; the problem is to land on the right source in the first place. Third, models achieving 88-96% accuracy on well-formed questions drop to 19-70% when questions contain subtle false premises, with the most vulnerable model accepting fabricated facts 64% of the time. We also identify a detection-accuracy paradox: the best false-premise detector ranks second in adversarial accuracy (abstention rate), while a weaker detector ranks first, showing that premise detection and answer recovery are partially independent capabilities. Overall, these suggest that high accuracy can mask systematic regional inequity, near-total dependence on retrieval infrastructure, and vulnerability to imperfect queries real users pose.

cs.CL↗

WebDS: An End-to-End Benchmark for Web-based Data Science

Many real-world data science tasks involve complex web-based interactions: finding appropriate data available on the internet, synthesizing multimodal data from different locations, and producing summarized analyses. Existing web benchmarks often focus on simplistic interactions and often do not require diverse tool-using capabilities. Conversely, traditional data science benchmarks typically concentrate on static, highly structured datasets and do not assess end-to-end workflows that encompass data acquisition, cleaning, analysis, and insight generation. In response, we introduce WebDS, the first end-to-end web-based data science benchmark. It comprises 870 web-based data science tasks across 29 diverse websites from structured government data portals to unstructured news media, challenging agents to perform complex, multi-step, tool-based operations, across heterogeneous data formats, to better reflect the realities of modern data analytics. Evaluations of current SOTA LLM agents indicate significant performance gaps in accomplishing these tasks. For instance, Browser Use, which accomplishes $80\%$ of tasks on WebVoyager, completes only 15% of tasks in WebDS, which our analysis suggests is due to new failure modes, such as poor information grounding, repetitive behavior and shortcut-taking that agents performing WebDS's tasks display. By contrast, humans achieve around 90% accuracy, highlighting a substantial gap between current agents and human performance. By providing a more robust and realistic testing ground, WebDS sets the stage for significant advances in the development of practically useful LLM-based data science.

cs.CL↗

NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews

Large Language Models (LLMs) have demonstrated impressive capabilities in generating coherent text but often struggle with grounding language and strategic dialogue. To address this gap, we focus on journalistic interviews, a domain rich in grounding communication and abundant in data. We curate a dataset of 40,000 two-person informational interviews from NPR and CNN, and reveal that LLMs are significantly less likely than human interviewers to use acknowledgements and to pivot to higher-level questions. Realizing that a fundamental deficit exists in multi-turn planning and strategic thinking, we develop a realistic simulated environment, incorporating source personas and persuasive elements, in order to facilitate the development of agents with longer-horizon rewards. Our experiments show that while source LLMs mimic human behavior in information sharing, interviewer LLMs struggle with recognizing when questions are answered and engaging persuasively, leading to suboptimal information extraction across model size and capability. These findings underscore the need for enhancing LLMs' strategic dialogue capabilities.

cs.CL↗

The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity

While generative models for music composition are increasingly capable, their adoption by musicians is hindered by text-prompting, an asynchronous workflow disconnected from the embodied, responsive nature of instrumental performance. To address this, we introduce Aria-Duet, an interactive system facilitating a real-time musical duet between a human pianist and Aria, a state-of-the-art generative model, using a Yamaha Disklavier as a shared physical interface. The framework enables a turn-taking collaboration: the user performs, signals a handover, and the model generates a coherent continuation performed acoustically on the piano. Beyond describing the technical architecture enabling this low-latency interaction, we analyze the system's output from a musicological perspective, finding the model can maintain stylistic semantics and develop coherent phrasal ideas, demonstrating that such embodied systems can engage in musically sophisticated dialogue and open a promising new path for human-AI co-creation.

cs.SD↗

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance

We study the capabilities of generative autoregressive transformer models trained on large amounts of symbolic solo-piano transcriptions. After first pretraining on approximately 60,000 hours of music, we use a comparatively smaller, high-quality subset, to finetune models to produce musical continuations, perform symbolic classification tasks, and produce general-purpose contrastive MIDI embeddings by adapting the SimCLR framework to symbolic music. When evaluating piano continuation coherence, our generative model outperforms leading symbolic generation techniques and remains competitive with proprietary audio generation models. On MIR classification benchmarks, frozen representations from our contrastive model achieve state-of-the-art results in linear probe experiments, while direct finetuning demonstrates the generalizability of pretrained representations, often requiring only a few hundred labeled examples to specialize to downstream tasks.

cs.SD↗

DiscoSum: Discourse-aware News Summarization

Recent advances in text summarization have predominantly leveraged large language models to generate concise summaries. However, language models often do not maintain long-term discourse structure, especially in news articles, where organizational flow significantly influences reader engagement. We introduce a novel approach to integrating discourse structure into summarization processes, focusing specifically on news articles across various media. We present a novel summarization dataset where news articles are summarized multiple times in different ways across different social media platforms (e.g. LinkedIn, Facebook, etc.). We develop a novel news discourse schema to describe summarization structures and a novel algorithm, DiscoSum, which employs beam search technique for structure-aware summarization, enabling the transformation of news stories to meet different stylistic and structural demands. Both human and automatic evaluation results demonstrate the efficacy of our approach in maintaining narrative fidelity and meeting structural requirements.

cs.CL↗

NewsEdits 2.0: Learning the Intentions Behind Updating News

As events progress, news articles often update with new information: if we are not cautious, we risk propagating outdated facts. In this work, we hypothesize that linguistic features indicate factual fluidity, and that we can predict which facts in a news article will update using solely the text of a news article (i.e. not external resources like search engines). We test this hypothesis, first, by isolating fact-updates in large news revisions corpora. News articles may update for many reasons (e.g. factual, stylistic, narrative). We introduce the NewsEdits 2.0 taxonomy, an edit-intentions schema that separates fact updates from stylistic and narrative updates in news writing. We annotate over 9,200 pairs of sentence revisions and train high-scoring ensemble models to apply this schema. Then, taking a large dataset of silver-labeled pairs, we show that we can predict when facts will update in older article drafts with high precision. Finally, to demonstrate the usefulness of these findings, we construct a language model question asking (LLM-QA) abstention task. We wish the LLM to abstain from answering questions when information is likely to become outdated. Using our predictions, we show, LLM absention reaches near oracle levels of accuracy.

cs.CL↗

NewsHomepages: Homepage Layouts Capture Information Prioritization Decisions

Information prioritization plays an important role in how humans perceive and understand the world. Homepage layouts serve as a tangible proxy for this prioritization. In this work, we present NewsHomepages, a large dataset of over 3,000 new website homepages (including local, national and topic-specific outlets) captured twice daily over a three-year period. We develop models to perform pairwise comparisons between news items to infer their relative significance. To illustrate that modeling organizational hierarchies has broader implications, we applied our models to rank-order a collection of local city council policies passed over a ten-year period in San Francisco, assessing their "newsworthiness". Our findings lay the groundwork for leveraging implicit organizational cues to deepen our understanding of information prioritization.

cs.IR↗

PatentEdits: Framing Patent Novelty as Textual Entailment

A patent must be deemed novel and non-obvious in order to be granted by the US Patent Office (USPTO). If it is not, a US patent examiner will cite the prior work, or prior art, that invalidates the novelty and issue a non-final rejection. Predicting what claims of the invention should change given the prior art is an essential and crucial step in securing invention rights, yet has not been studied before as a learnable task. In this work we introduce the PatentEdits dataset, which contains 105K examples of successful revisions that overcome objections to novelty. We design algorithms to label edits sentence by sentence, then establish how well these edits can be predicted with large language models (LLMs). We demonstrate that evaluating textual entailment between cited references and draft sentences is especially effective in predicting which inventive claims remained unchanged or are novel in relation to prior art.

cs.CL↗

Explaining Mixtures of Sources in News Articles

Human writers plan, then write. For large language models (LLMs) to play a role in longer-form article generation, we must understand the planning steps humans make before writing. We explore one kind of planning, source-selection in news, as a case-study for evaluating plans in long-form generation. We ask: why do specific stories call for specific kinds of sources? We imagine a generative process for story writing where a source-selection schema is first selected by a journalist, and then sources are chosen based on categories in that schema. Learning the article's plan means predicting the schema initially chosen by the journalist. Working with professional journalists, we adapt five existing schemata and introduce three new ones to describe journalistic plans for the inclusion of sources in documents. Then, inspired by Bayesian latent-variable modeling, we develop metrics to select the most likely plan, or schema, underlying a story, which we use to compare schemata. We find that two schemata: stance and social affiliation best explain source plans in most documents. However, other schemata like textual entailment explain source plans in factually rich topics like "Science". Finally, we find we can predict the most suitable schema given just the article's headline with reasonable accuracy. We see this as an important case-study for human planning, and provides a framework and approach for evaluating other kinds of plans. We release a corpora, NewsSources, with annotations for 4M articles.

cs.CL↗

Are Large Language Models Capable of Generating Human-Level Narratives?

This paper investigates the capability of LLMs in storytelling, focusing on narrative development and plot progression. We introduce a novel computational framework to analyze narratives through three discourse-level aspects: i) story arcs, ii) turning points, and iii) affective dimensions, including arousal and valence. By leveraging expert and automatic annotations, we uncover significant discrepancies between the LLM- and human- written stories. While human-written stories are suspenseful, arousing, and diverse in narrative structures, LLM stories are homogeneously positive and lack tension. Next, we measure narrative reasoning skills as a precursor to generative capacities, concluding that most LLMs fall short of human abilities in discourse understanding. Finally, we show that explicit integration of aforementioned discourse features can enhance storytelling, as is demonstrated by over 40% improvement in neural storytelling in terms of diversity, suspense, and arousal.

cs.CL↗

Autoregressive Transformers for Disruption Prediction in Nuclear Fusion Plasmas

The physical sciences require models tailored to specific nuances of different dynamics. In this work, we study outcome predictions in nuclear fusion tokamaks, where a major challenge are \textit{disruptions}, or the loss of plasma stability with damaging implications for the tokamak. Although disruptions are difficult to model using physical simulations, machine learning (ML) models have shown promise in predicting these phenomena. Here, we first study several variations on masked autoregressive transformers, achieving an average of 5\% increase in Area Under the Receiving Operating Characteristic metric above existing methods. We then compare transformer models to limited context neural networks in order to shed light on the ``memory'' of plasma effected by tokamaks controls. With these model comparisons, we argue for the persistence of a memory throughout the plasma \textit{in the context of tokamaks} that our model exploits.

physics.plasm-ph↗

Tracking the Newsworthiness of Public Documents

Journalists must find stories in huge amounts of textual data (e.g. leaks, bills, press releases) as part of their jobs: determining when and why text becomes news can help us understand coverage patterns and help us build assistive tools. Yet, this is challenging because very few labelled links exist, language use between corpora is very different, and text may be covered for a variety of reasons. In this work we focus on news coverage of local public policy in the San Francisco Bay Area by the San Francisco Chronicle. First, we gather news articles, public policy documents and meeting recordings and link them using probabilistic relational modeling, which we show is a low-annotation linking methodology that outperforms other retrieval-based baselines. Second, we define a new task: newsworthiness prediction, to predict if a policy item will get covered. We show that different aspects of public policy discussion yield different newsworthiness signals. Finally we perform human evaluation with expert journalists and show our systems identify policies they consider newsworthy with 68% F1 and our coverage recommendations are helpful with an 84% win-rate.

cs.CL↗

Stay on topic with Classifier-Free Guidance

Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q\&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75\% preference for GPT4All using CFG over baseline.

cs.CL↗