subject

cs.CY

cs.CY: explore 271 source-linked works published from 2013 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval

Artificial intelligence (AI) hiring tools have revolutionized resume screening, and large language models (LLMs) have the potential to do the same. However, given the biases which are embedded within LLMs, it is unclear whether they can be used in this scenario without disadvantaging groups based on their protected attributes. In this work, we investigate the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection. Using that framework, we then perform a resume audit study to determine whether a selection of Massive Text Embedding (MTE) models are biased in resume screening scenarios. We simulate this for nine occupations, using a collection of over 500 publicly available resumes and 500 job descriptions. We find that the MTEs are biased, significantly favoring White-associated names in 85.1\% of cases and female-associated names in only 11.1\% of cases, with a minority of cases showing no statistically significant differences. Further analyses show that Black males are disadvantaged in up to 100\% of cases, replicating real-world patterns of bias in employment settings, and validate three hypotheses of intersectionality. We also find an impact of document length as well as the corpus frequency of names in the selection of resumes. These findings have implications for widely used AI tools that are automating employment, fairness, and tech policy.

cs.CY↗

arXiv2026

Emerging Media Use and Acceptance of Digital Immortality: A Cluster Analysis among Chinese Young Generations

Digital immortality is increasingly discussed as a technological possibility, yet empirical evidence about potential users' evaluations remains limited. We surveyed 462 Chinese young adults, combining cluster analysis of four emerging-media use frequencies with valence coding of open-ended responses to physical death, physical immortality, digital immortality, and digital death. Three profiles emerged: broad emerging-media, gaming-focused, and low-use users. Broad emerging-media users reported the highest adjusted acceptance and scored higher on several personality and worldview measures, while fear of death did not differ across profiles. Physical immortality elicited the most negative responses; digital immortality produced more mixed, less negative appraisals. More favorable digital-immortality appraisals predicted higher acceptance after adjustment for media-use profile and demographics, although scenario valence did not differ across profiles. The findings distinguish general receptivity associated with emerging-media repertoires from emotional responses to specific imagined futures, showing that evaluations depend on the form of continuity envisioned.

cs.CY↗

arXiv2026

ACE-Align: Attribute Causal Effect Alignment for Cultural Values under Varying Persona Granularities

Ensuring that large language models (LLMs) reflect diverse cultural values is important for globally deployed NLP systems. However, existing approaches often treat cultural groups as homogeneous and overlook within-group heterogeneity arising from intersecting demographic attributes, leading to unstable behavior under varying persona granularity. To address this gap, we propose ACE-Align (Atribute Causal Effect Alignment), a causally inspired framework based on controlled persona edits that aligns how specific demographic attributes shift different cultural values, rather than treating each culture as a homogeneous group. We evaluate ACE-Align across 14 countries spanning five continents, with personas specified by subsets of four attributes (gender, education, residence, and marital status) and granularity instantiated by the number of specified attributes. Across all persona granularities, ACE-Align consistently outperforms baselines. Moreover, in within-survey comparisons, it reduces the average Global North--South alignment gap from 3.40 to 1.11 points on WVS and from 2.53 to 0.85 points on ISSP. Code and dataset are released at https://github.com/Wells-Luo/ACE-Align.

cs.CY↗

arXiv2026

Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models

We propose a novel perspective for probing LLM sycophancy in a direct and neutral way, mitigating various forms of uncontrolled bias, noise, or manipulative language, deliberately injected to prompts in prior works. A key novelty of our approach is the use of an LLM-as-a-judge in a zero-sum betting game. Within this framework, sycophancy serves one individual (the user) while explicitly incurring cost on another. Comparing 11 leading models we find that while most models exhibit significant sycophantic tendencies in the common setting, in which sycophancy is self-serving to the user and incurs no cost on others, seven of the models exhibit ``moral remorse'', five of which significantly over-compensate for their sycophancy in case it explicitly harms a third party. We refer to this phenomenon as `anti-sycophancy' bias and discuss possible causes for this shift.

cs.AI↗

arXiv2026

Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues

A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as students, which can facilitate tutor model evaluation and training. Existing work mostly focuses on within-dialogue simulation, which lacks context on student knowledge and behavior, partly due to not grounding in past student question-answering or dialogue interactions. In this work, we introduce the task of history-conditioned student simulation, where the goal is to accurately predict student dialogue turns by leveraging information in the student's learning history. We propose a two-component framework in which a profile generator summarizes a student's history and a simulator predicts student turns conditioned on the resulting profile. We train both components with reinforcement learning (RL), yielding profiles optimized for faithful student simulation. We evaluate our method and baselines on the first-of-its-kind real-world dataset of student dialogues and question responses that we collect from a math learning platform. Extensive experiments show that our method significantly outperforms baselines, and demonstrate the importance of history, profiles, and RL training.

cs.CL↗

arXiv2026

From AGI to ASI

Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI organisations. Achieving this goal would have profound and far-reaching impacts on human society, which raises many complex questions for the decade ahead. This report investigates how AI itself might continue to develop in a post-AGI world along the continuum of machine intelligence. The endpoint of this continuum, Universal AI, is theoretically well understood, which provides some formal grounding for the main focus of this report: the transition from human-level AGI to artificial general superintelligence, which can intuitively be understood as a system that is more intelligent and cognitively capable than large organisations of humans. After characterizing ASI, the report discusses four potential pathways from AGI to ASI: scaling AGI, AI paradigm shifts, recursive improvement, and ASI emerging from large-scale multi-agent collectives. The report then discusses possible frictions and bottlenecks along these pathways. Determining whether the impact of these frictions will be negligible or substantial raises a number of concrete open research questions. Due to large uncertainties for predicting ASI progress, it cannot be ruled out that AI progress might continue to accelerate over the next years. This could imply that the image of a single transformative step change, caused by the introduction of human-level AGI into our society, could be inaccurate. More apt might be the prospect of a series of transformative societal changes caused by AI-enabled progress and breakthroughs across many areas of science and technology. Preparing for this prospect requires a massively interdisciplinary endeavour of global scope and interest.

cs.AI↗

arXiv2026

Atom Learning Model (ALM): how a real classroom got tokenised

The Atom Learning Model (ALM) tokenises a school curriculum. 757 pages of GCSE and Further Mathematics material were read by machine into 1,934 atoms, each one thing a learner can do in a single step, ordered by 4,616 machine-written prerequisite links. Both sides of a lesson are then expressed in that one structure: a question is a set of atoms plus everything beneath them, a child's ability is a score between 0 and 1 on every atom of the same graph, and whether a question suits a child is arithmetic over one index, with no difficulty parameter fitted for either side. Nobody wrote an atom, a link or a question. Reading the 757 pages cost £55, building the whole structure cost between £615 and £1,230, and against it the system composed 6,648 questions for 373 children in two English secondary schools over seven weeks, at 26p per composed question. Four measurements went against expectation. The cost is in the links, not the pages. The composer's own difficulty label has a rank correlation of -0.0123 with measured facility, so a language model shown a question cannot say how hard it is. Children stop working when a mark takes seven seconds instead of three. And the deployment never served a question deeper than two prerequisite steps, which is exactly where the central premise becomes testable, leaving it unfalsified rather than confirmed.

cs.CY↗

arXiv2026

Applications of Risk Science to AI Fairness Evaluation: Principles, Challenges, and Best Practices

Scholarly work which aims to describe potential societal impacts (e.g., risks) of proliferating technology (especially related to artificial intelligence or other algorithmic systems) is likely to have an impact beyond the scientific communities it was written for, given that general society itself is a primary object of study. However, it is an open question whether the current practices of AI evaluation scholarship follow the principles and best practices established by risk science, which aims to systematically generate knowledge related to understanding, assessing, communicating, managing, and governing risk. In this work, we examine this in depth by conducting a literature review of scholarly works purporting to evaluate the bias or fairness of technological systems used for tasks related to hiring and employment. Through analysis of 22 common fairness evaluation metrics and studies using them, we find that most characterize the severity of bias- or fairness-related consequences but do not follow best practices to characterize the uncertainty around either the occurrence of these consequences or severity estimates. Next, we conduct a case study of fairness evaluation for an AI-mediated resume screening task and demonstrate how principles of risk science can be incorporated into such an evaluation. Finally, we propose the AI Risk Report Card, which facilitates the reporting and communication of risk assessment results to stakeholders in positions to act based on the predicted risks. The outcomes of these activities suggest that further research at the convergence of risk science and AI evaluation can lead to advancements in AI assessments of societal impact by enabling shared frameworks to evaluate and discuss AI risks both within and outside of the scientific community.

cs.CY↗

arXiv2026

LLM Judges as Raters: A Pre-Registered Audit of Severity, Halo, Reliability, and Version Instability in LLM Essay Scoring on Public Corpora

Large language models (LLMs) are increasingly used as essay graders in learning analytics, evaluated almost exclusively with agreement statistics. Educational measurement warns that raters also differ in severity, show halo, and drift as instruments. We treat LLM judges as raters and run a pre-registered rater-effects battery (many-facet Rasch severity, residual halo, generalizability/decision studies, cross-version shifts, differential functioning) on public corpora in two languages (ENEM/Essay-BR; ASAP): 2,377 essays, 12 judges, 4 providers, 5 version contrasts, replicated cells, released as a score tensor. Judge severity spans 219 points on ENEM's 0-1000 scale; on ASAP the panel spread is 15-33% of the score range against a between-trained-human gap near 1%. Judge-human correlations sit in an undiscriminating .47-.56 band. All five version contrasts shift severity beyond a family-wise permutation null (up to 133 points), and one judge was deprecated mid-study, caught by identity canaries. Two pre-registered tests returned honest nulls: severity-adjusted leaderboard reversals did not survive a permutation null, and "silent drift" was refuted: agreement moved with severity in four of five contrasts. Replication yields self-consistency (phi>=.80 at k<=2) but not human-level accuracy, and a same-instrument check overturned our own halo comparison: matched on instrument and calibration, we find no credible evidence that judge halo exceeds the trained-human range.

cs.CL↗

arXiv2026

MMMMM: A Unified Taxonomy for Investigating the Mechanisms of Multilingual MultiModal Misinformation

Multimodal misinformation on social media is highly prevalent, potent, and harmful, yet difficult to detect and counter, and still poorly understood compared to its text-only counterpart. Research on the properties and deceptive strategies of multimodal misinformation is hindered by a lack of taxonomies grounded in real-world contexts and by the limitations of current multimodal machine learning models, which prevent the automation of annotation and analysis at scale. We address these shortcomings in three steps. First, we collect a large-scale, high-quality dataset of real-world misinformation instances from Twitter/X in seven languages. Second, we develop a novel, comprehensive taxonomy of multimodal misinformation grounded in an in-depth qualitative analysis of the data and prior theoretical work. Finally, we operationalise the taxonomy through an automated multi-step annotation pipeline using a Vision-Language Model (VLM), and perform human-validation. Our novel approach leads to previously undocumented insights about how social media users combine images with text to spread misinformation in the wild, e.g., that AI-generated content is particularly prevalent in technology and science, while vaccination misinformation disproportionately utilises images from news outlets to assert credibility. Our method and findings provide guidance for targeted approaches for detecting multimodal misinformation, and suggest that mitigation efforts should be developed and applied strategically rather than uniformly.

cs.CY↗

arXiv2026

Text Data Analysis and Classification Methods - Insights from Customer Letters in Life Insurance

The business of life insurance companies is characterized by long-term contracts. For this reason, data describing customers is of immense value. A portion of the data provided to the customer is rarely or not at all analyzed. This includes customer letters of any kind. This work focuses on classifying customer letters as cancellations and identifying the respective reason, if available. The outlined approach can also be applied to other business transactions and reasons. We discuss data acquisition and preparation, present alternatives, and explain the reasons for the chosen approach. A successful implementation of such a tool can lead to a better understanding of customer cancellation behavior by the insurer, enabling more targeted actions in certain situations.

stat.AP↗

arXiv2026

Large-Scale Qualitative Research with AI: Infrastructure, Management and Operation of the Socioscope Data Pipeline

The Socioscope project is a pioneering effort in Large-Scale Qualitative Research (LSQR) collecting comparable, open-ended, multimedia field data on hundreds of cases and using AI to make the material analysable at scale. The domain studied is the food system. The entities documented are the organisations that act in it: farms, processors, distributors, retailers, restaurants; and, at meso level, the actors that shape their environment, such as municipalities, government programmes, banks, NGOs and universities. This paper provides the technical reference for how the resulting data Corpus was built and managed to enable AI-augmented analysis. It describes the data pipeline end to end: the systemic sampling frame; the transaction grid used to capture each initiative's relations within the food system; the social contract that rewards participating interviewees, aiming to sustain access; the operational chain from scouting to interviews, including their uploading, transcription, translation, quality control and curation; the provenance rules (originals are immutable, every transformation is logged); and the installation of equipment, personnel and processes, including ethics and GDPR compliance. In its first phase (2023-2026) the pipeline produced 686 documented cases from 31 countries: some 1,430 hours of recordings, about 450,000 speech turns, and 12.6 million words of transcript. We report costs, metrics, lessons learned and limitations, so that other teams can reuse, adapt, and improve the Socioscope methodology.

cs.CY↗

arXiv2026

Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments

Large language models (LLMs) are increasingly deployed as proxies for human participants in social simulations, yet whether they update their beliefs in response to persuasive arguments, as humans do, remains poorly understood. We conduct a systematic comparison using a naturally occurring online persuasion corpus in which original posters explicitly verify whether a reply changed their view. Our results show that LLMs achieve only slight agreement with humans (Cohen's kappa ranging from 0.079 to 0.178). Content-level analyses show that humans and LLMs agree on the strongest persuasion cues but diverge on finer ones: humans are more swayed by novel content and assertive language, whereas LLMs favor topical similarity and surface-level formatting. At the level of persuasion strategy, LLMs underweight emotional appeals and overweight credibility signals relative to humans, while the type of proposition under debate exerts no measurable effect on the degree of divergence. Furthermore, switching from first-person role-playing to third-person observation shifts all models toward greater resistance to persuasion, with the effect varying across persuasion strategies and textual features. These findings highlight the risk of treating LLM judgments as faithful proxies for human belief updating and point to structural differences in how LLMs and humans process persuasive discourse. Our code is available at https://github.com/tsinghua-fib-lab/LLM-belief-update-cmv.

cs.CY↗

arXiv2026

Verification-Time Dependency on a Disappearing Evaluator

AI governance and assurance often assume that a consequential model-mediated decision can be reconstructed or tested after the fact. That assumption may fail when the evaluator that produced the decision is no longer accessible in the same version and execution context. This paper develops three verification-time constructs derived from Execution Governance (EG) 3.0: Decision-State Commitment, Independent Verifiability, and Counterfactual Auditability. Independent reprocessing of released Study 2 artifacts reproduces two original within-family behavioural comparisons: 52.0% modal-decision reversal for Llama 3.1 8B versus Llama 3.3 70B (26/50) and 30.0% for GPT-OSS 20B versus GPT-OSS 120B (15/50). The corrected baseline establishes that these are within-family comparisons, not provider-established succession. Post-hoc re-pairing against Groq-designated migration paths yields 64.0% and 38.0% reversal, but these figures remain descriptive because the cross-family invocation parameters were asymmetric. A 22-event retirement census independently recomputes to median 16.45 months, mean 18.72 months, range 3.9-40.3 months, with 17/22 intervals below 24 months, while also showing that evaluator availability can differ by service surface. The joint contribution is an operational verification-time protocol and optional Verification-Time Preservation Package (VTPP) specifying what evidence to bind at authorization time, what a separately trusted verifier can substantiate later, how stability and paired counterfactual tests should be calibrated, and which semantic checks remain beyond JSON Schema validity. The protocol is downstream and non-authorizing: it does not alter the EG Core Formula, add a seventh live condition, or state jurisdiction-specific legal admissibility.

cs.CY↗

arXiv2026

The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interface

When a generative search interface answers a commercial question, which market's products it names is decided before the model reasons about the products. We report a controlled probe of 234 runs against the logged-out ChatGPT web interface and the OpenAI API, collected on 29 and 30 August 2026 across four exit countries and six query languages, with six identical runs per cell. Three results. First, the top recommendation is unstable: it changed across six identical runs on four of six prompts, and that rate was identical in the browser interface and in the API with web search both enabled and disabled, so instability is a property of the system and not of the surface. Second, query language, and not location, decides whether local suppliers appear at all. Where the query language matched the country, a global brand won 1 of 24 runs; asked in English on the same connections, local brands took 0 of 6 runs in Estonia and Turkiye. Third, language and location are separable and act on different things: holding the query language fixed and moving only the exit IP moves the market whose brands are named while the answer stays in the query language. We show this on two unrelated pairs, Turkish asked from Berlin and Russian asked from Tallinn, and in both the answer names the resident country's suppliers. A minority language occupies a middle tier: Russian asked from Estonia names an Estonian supplier in 4 of 6 runs and a global one in all six, where Estonian names a local supplier in every run and English names none. A negative control in a second category, coded with the same instrument, shows no language effect at all, and disconfirms our own expectation: that category does have domestic suppliers and none was named in any language, which points the explanation at whether a category is nationally regulated rather than at whether it is nationally supplied.

cs.IR↗

arXiv2026

AMINA: The Inclusive and Accountable AI for Marginalized Immigrant Nonprofit Assistance

Immigrant-led nonprofit groups, particularly those operating in politically sensitive contexts, face exclusion from formal registries and digital platforms. This paper reports a three-phase mixed-methods study with Iranian immigrant nonprofit practitioners: 27 semi-structured interviews, a co-design session, and 7 evaluation and feedback interviews on a prototyped AI assistant, AMINA. Our findings highlight how legitimacy barriers, capacity gaps, and politically charged misinformation constrain nonprofit operations. We translate these insights into design goals for an inclusive nonprofit AI assistant: support for everyday group operations, recognition of informal nonprofit efforts, proactive countering of misinformation, and multilingual, accessible interaction. User evaluations show AMINAs potential to reduce reporting burdens and foster transparency through proactive reminders, and catalyze collaboration across dispersed networks. We contribute to CSCW and HCI by characterizing the cooperative work of transnational immigrant nonprofits, extending scholarship on informality and misinformation, and demonstrating how AI can act as a collaborative partner that strengthens, rather than displaces, the human connections at the core of nonprofit ecosystems, while also posing major risks.

cs.CY↗

arXiv2026

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which safety behaviors are implemented remain poorly understood. We study LLM safety from a mechanistic interpretability perspective and characterize a multi-stage *safety circuit* that organizes refusal behavior, consisting of (i) $\textbf{Harmful Detection Heads}$ that respond to harmful inputs, (ii) $\textbf{Safety Neurons}$ that mediate and stabilize safety signals in the residual stream, and (iii) $\textbf{Refusal Heads}$ that translate these signals into safe response generation. Using targeted attention-head and neuron-level interventions, we provide causal evidence consistent with this circuit organization, showing that suppressing upstream Harmful Detection Heads disrupts downstream refusal behavior and that safety neurons mediate this interaction. We validate that this decomposition recurs across multiple LLM architectures and adversarial attack settings, and use simple, architecture-preserving weight scaling as a mechanistic probe to test its functional relevance. Across six LLMs, circuit-guided scaling improves safety rates under attacks by 26.5%, while incurring only a 1.7% accuracy drop across four standard benchmarks. Overall, our results support a circuit-level interpretation of LLM safety and suggest that mechanistic abstractions can reveal stable and transferable patterns underlying aligned behavior.

cs.CL↗

arXiv2026

Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priors

Understanding how people perceive urban environments is essential for inclusive planning, yet conventional surveys are costly and difficult to scale. We investigate whether Multimodal Large Language Models (MLLMs) can assess perceived urban safety from street-view imagery while accounting for the observer-dependent nature of perception. Using Place Pulse 2.0, we evaluate four open and proprietary MLLMs across 56 cities under a Neutral prompt and socio-demographic personas defined by gender, age, and race or ethnicity. We also analyse the keywords generated to justify each classification. All four models display comparable zero-shot capability, with city-macro F1 scores of 65--69%, and preserve meaningful cross-city variation. However, they systematically favour the Safe class, underpredict unsafety, and compress differences between cities. Their explanations converge on a shared visual lexicon: maintenance, greenery, order, and residential character support Safe judgements, whereas deterioration, isolation, poor lighting, and limited pedestrian activity support Unsafe judgements. Persona prompting produces substantial and structured shifts while holding the image fixed. Female personas yield more Unsafe classifications than Male personas across all models; age effects are model-dependent, although Middle-aged personas generally remain closest to Neutral. Black/African American and Native American personas frequently show the largest departures, while the closest race or ethnicity match varies by model. These findings show that MLLMs can provide scalable signals of perceived urban safety, but not from a demographically neutral standpoint.

cs.CY↗

Compare source metadata on this page

Work	Published	Source identifier	Source
Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval	2026-08-30	2407.20371	arxiv
Emerging Media Use and Acceptance of Digital Immortality: A Cluster Analysis among Chinese Young Generations	2026-08-30	2505.01355	arxiv
ACE-Align: Attribute Causal Effect Alignment for Cultural Values under Varying Persona Granularities	2026-08-30	2601.12962	arxiv
Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models	2026-08-30	2601.15436	arxiv
Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues	2026-08-30	2605.30051	arxiv
From AGI to ASI	2026-08-30	2606.12683	arxiv
Atom Learning Model (ALM): how a real classroom got tokenised	2026-08-30	2608.21106	arxiv
Applications of Risk Science to AI Fairness Evaluation: Principles, Challenges, and Best Practices	2026-08-30	2608.29478	arxiv
LLM Judges as Raters: A Pre-Registered Audit of Severity, Halo, Reliability, and Version Instability in LLM Essay Scoring on Public Corpora	2026-08-30	2608.29517	arxiv
MMMMM: A Unified Taxonomy for Investigating the Mechanisms of Multilingual MultiModal Misinformation	2026-08-30	2608.29681	arxiv
Text Data Analysis and Classification Methods - Insights from Customer Letters in Life Insurance	2026-08-30	2608.29699	arxiv
Large-Scale Qualitative Research with AI: Infrastructure, Management and Operation of the Socioscope Data Pipeline	2026-08-30	2608.29751	arxiv
Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments	2026-08-30	2608.29803	arxiv
Verification-Time Dependency on a Disappearing Evaluator	2026-08-30	2608.29912	arxiv
The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interface	2026-08-30	2608.30052	arxiv
AMINA: The Inclusive and Accountable AI for Marginalized Immigrant Nonprofit Assistance	2026-08-30	2608.30084	arxiv
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling	2026-08-30	2609.00051	arxiv
Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priors	2026-08-29	2503.00610	arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.