Papers

Large language model (LLM) trading agents show promising performance in equity markets, yet remain narrowly focused on US equities with little evidence from live deployment. We present Fin-Analyst, a hybrid agent for FinMMEval 2026 Task 3: an eight-specialist LLM pipeline over news, SEC filings, fundamentals, analyst forecasts, technical indicators, and social sentiment, aggregated by a Meta-Agent for Tesla (TSLA), and a lightweight rule based three-signal vote for Bitcoin (BTC). On the final official leaderboard (accessed 2026-07-05), Fin-Analyst ranks first of all agents on TSLA with a +13.51% return, +28.33 points over Buy-and-Hold (Sharpe 4.10, 88% win rate), while the BTC vote ends flat yet well above a sharply falling baseline. Relative to the interim performance, the asset ranking reversed, indicating that short live windows yield volatility-sensitive rankings. Ablation identifies event-driven 8-K disclosures as the most influential TSLA signal. Error analysis shows that the memoryless agents repeat wrong calls for days at a time, and that the fixed-threshold BTC rules lost money by trading on noise in a sideways market while the LLM pipeline gained under similar conditions, motivating a memory-aware, LLM-based successor for both assets.

Retrieval-augmented speech translation improves rare terminology, but systems such as RASST still assume that users provide a glossary before each session. That assumption is inconvenient for live talks, while merging every domain into one growing glossary eventually places too many irrelevant terms in the same retrieval and prompt competition. We present AutoTerm-SST, an interactive system that removes session-time glossary upload and domain selection. It organizes a large offline terminology catalog into topic slices, matches recent streaming translation context to bilingual slice prototypes, and activates a compact multi-slice working set under fixed retrieval and prompt budgets. On five ACL and five ESO oncology talks, AutoTerm matches a known-domain reference in terminology accuracy (88.3% vs. 88.1%) and mWER-resegmented BLEU (45.09 vs. 45.19), while requiring no domain input. Compared with a one-million-entry merged glossary, it improves terminology accuracy by 3.9 points and BLEU by 2.30. Routing plus four-slice retrieval remains lightweight: the complete system runs at 0.406 RTF, and the vLLM host sustains 32 real-time sessions. The live demo exposes active slices and retrieved terminology as the topic changes, providing zero-setup terminology-aware streaming translation.

We ask whether relation-type information (e.g., capital-of) and entity-specific information (e.g., France to Paris) become causally active at the final-token position at the same depth during recall. Using four complementary causal diagnostics across four decoder-only models and eight prompt families, we find a robust temporal asymmetry: relation information becomes generation-controlling before entity information does. Relation onset precedes entity onset by 10-16 tested layers (31-44% of network depth) at threshold 0.4, with the ordering holding across all 16 model-threshold combinations for thresholds 0.2-0.5. Critically, entity information is not absent early: entity-token patching succeeds at 90-100% in early layers. Instead, entity commitment to generation is deferred: entity information is available at the entity-token position but becomes generation-controlling at the final token only after being routed there.

Cognitive Stimulation Therapy (CST) offers non-pharmacological support for elders with cognitive impairment, yet scalability remains constrained by reliance on trained facilitators and severe data scarcity, particularly for privacy-sensitive, low-resource languages such as Cantonese. While Large Language Models (LLMs) show promise for automated companionship, they often struggle to balance empathetic engagement with adherence to cognitive stimulation guidelines. We propose a framework addressing these challenges along two complementary axes. First, STaR-CS (Style-Transfer and Role-Conditioned Cognitive Stimulation) synthesizes multi-party dialogues through facilitator style modeling and structured skeleton extraction, mitigating data barriers. Building upon this corpus, the Reflective Cognitive Alignment (RCA) framework models stimulation interactions as a sequential decision process, integrating Protocol-Constrained Chain-of-Cognition (PC-CoC) for structured reasoning and Inference-Time Value Alignment (IVA) for principled response selection based on safety and engagement goals. Evaluations across six backbone LLMs and two independent judges show that RCA consistently improves protocol adherence, safety, and group facilitation over standard prompting baselines. Our code is available at https://github.com/jiangjyjy/RCA_Agent.

The paper imports the Kontsevich Segal Witten criterion from quantum gravity into machine learning to evaluate complex linear maps Standard techniques analyze magnitude or positive definiteness whereas this method exclusively limits the collective phase of a spectrum The researchers create three distinct differentiable certificates comprising a determinant sector a subset product envelope and the full criterion The subset envelope prevents all exterior power eigenvalues from touching the negative real axis This constraint precisely matches the accept or reject choices of an exponential minor enumeration while reducing processing expenses drastically The team provides a differentiable enforcement application via a Schur parameterization The document also identifies crucial boundaries regarding where this system works The constraint cannot balance deep linear propagation since restricting the phase budget damages eigenvector conditioning Furthermore the technique remains completely blind to magnitude based targets like normalizing flow likelihoods Thus researchers must restrict this tool specifically to models that process the argument of a spectral product

Automated creativity assessment has been a long standing challenge, with traditional methods often being resource intensive or lacking practical accuracy. We introduce a novel approach by using Poly-Encoder for computationally efficient and accurate automated creativity assessment. We fine-tuned a Poly-Encoder on a public dataset from the Scientific Creative Thinking Test, comprised of approximately 18,000 human-rated question responses. Our method leverages small pre-trained BERT encoders, achieving performance comparable to fine-tuned Large Language Models while significantly reducing computational demands. Experiments with the BERT-family models and poly-code counts achieved Pearson correlations of up to r = 0.74, 95% CI [0.73, 0.75] with human raters, matching the performance of resource intensive LLMs. This study bridges the gap between high performance and computational efficiency, potentially enabling widespread implementation of automated creativity assessment on accessible consumer-grade hardware. With some limitations, our findings suggest that Poly-Encoders are a promising alternative to LLMs for practical, scalable creativity assessment in various contexts, especially educational.

With the unprecedented success of Language Models (LMs), the science of Prompt Engineering has evolved the powerful idea of Prompt Programming, where prompts are treated as a programmable control surface for describing complex tasks and leveraging LM capabilities. However, existing prompt programming frameworks suffer from various complexities and inelegances, which make them hard to utilize in practice for effectively describing tasks. We propose Imprompt, a new language framework for the study and practice of prompt programming. We undertake a foundational investigation of prompt programming, and contend that prompt programs must contain only the task descriptions and must be decoupled from lower-level 'execution' details. We further develop this position by illustrating structured prompting as a combination of prompt programming and prompt program 'compilation'. We exemplify this view by formally defining two compilers for Imprompt programs. We then explore the idea of typing for prompt programs and draw a correspondence between type checking and constrained decoding. Finally, we implement our compilers and type checkers and evaluate them on a variety of case studies. We believe our work contributes programming-language foundations toward the emerging area of prompt programming.

We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185 risk variants into a CIA-triad-grounded hierarchy and is cross-validated against three well-established OWASP guidelines. Based on this taxonomy, we construct a benchmark suite spanning 133 languages, comprising over 93K purpose-built samples targeting both user queries and agent responses, along with 3,435 cross-source samples adapted from five public agent-security datasets. To detect these operational threats in practice, we develop a dual-mode approach combining SFT-based generative reasoning for interpretable offline auditing with discriminative classification heads on the frozen backbone, enabling real-time detection at approximately 50,ms. We release four models with 0.8B, 2B, 4B, and 9B parameters, all achieving $\geq$94% F1 on purpose-built benchmarks and surpassing the strongest competing guardrails by 6 to 12 absolute points. On cross-source evaluation, the 9B model attains 91.29% F1 with a more balanced precision–recall trade-off. Moreover, ablation experiments show that classification heads can equip a guardrail with risk detection capabilities beyond its original scope and achieve state-of-the-art performance. These results demonstrate the extensibility of the approach and its generality as a plug-in enhancement.

Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task. This creates a practical allocation problem: every token spent on coordination is unavailable to task instructions or evidence when a call is assembled under a fixed context budget. We introduce the Roundtable Context Window Test (RCWT), a controlled protocol for measuring this task-budget displacement effect. RCWT varies coordination content while controlling total budget, position order, task family, and scoring. In the main context-dependent recall task at $W=4096$, three commercial models remain near baseline through moderate overhead and then degrade sharply once residual reference evidence falls to a few hundred tokens. Window-scaling summaries are consistent with a task-specific residual-budget interpretation rather than a fixed percentage threshold, but we treat this as descriptive evidence rather than a universal law. To test whether the fixed-budget cliff persists when task evidence remains intact, we add an intact-task ablation: the full task/reference block is kept present while coordination tokens increase by expanding total prompt length. In that setting, all tested calls return every scored field correctly across GPT-4.1-mini, Claude Haiku 4.5, and Gemini 2.5 Flash up to a 95% coordination ratio. This ablation narrows the claim: the main RCWT cliff is best read as task-budget displacement, not as proof that coordination volume alone causes semantic interference in the original open-ended task. RCWT is therefore a measurement primitive for context-allocation budgeting, not a complete theory of multi-agent benefit or session-level coordination.

Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LLMs) offer new opportunities by processing extensive textual contexts, but pretraining of these models can induce latent "personality-like" biases, making single-model inferences inconsistent. We propose a fine-tuned multi-agent framework for detecting OCEAN personality traits, in which sub-agents are conditioned to adopt high, low, or neutral perspectives for each trait through masked language modeling (MLM) and psychometric supervision. A judge LLM aggregates and compares sub-agent outputs to generate final trait predictions, capturing multiple complementary perspectives while mitigating individual model biases. We evaluate the framework on life narrative dataset through quantitative and qualitative experiments, including baselines, ablations, and inference quality analyses. Our approach offers a scalable and interpretable method for text-based personality inference, highlighting the benefits of multi-agent reasoning grounded in psychometric supervision.

Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared semantic search dynamics between humans and three large language models (GPT-4o, Gemini-2.5-Pro, Claude-Sonnet-4.5) using verbal fluency data. By applying trajectory-based NLP metrics to the items generated by 82 human participants and LLM output across eight temperature settings, we quantified three complementary dimensions: entropy (step size predictability), distance to next (successive semantic steps), and distance to centroid (global dispersion). Humans exhibited higher entropy, larger semantic steps and broader dispersion than all LLMs, indicating more variable and exploratory search. Temperature tuning produced only partial alignments, as individual metrics matched between humans and LLMs at specific settings, but no configuration reproduced the complete human profile (in all dimensions). These findings suggest that human semantic search implements a distinctive balance between local exploitation and global exploration that current model architectures fail to reproduce.

Embodied accounts of semantic memory highlight the role of sensorimotor systems in acquiring and storing knowledge. Congenitally blind populations offer a critical test bed for these assumptions, providing an opportunity to assess whether conceptual grounding requires visual experience. In this study, we assessed semantic memory navigation differences between blind and sighted individuals using a property listing task with concrete and abstract concepts. We computed semantic entropy, an embedding-based natural language processing metric that captures the predictability of retrieval. Generalized linear mixed models revealed distinct navigation patterns across groups: while sighted individuals showed higher entropy for abstract than concrete concepts, blind participants did not. Instead, blind individuals exhibited higher entropy for visually salient concrete concepts (e.g., penguin). These results underscore the role of visual experience in the organization and dynamic navigation of semantic memory.

Intercomprehension refers to partial intelligibility of an unfamiliar language (L2) by a speaker of a related language (L1). How is this zero-shot cross-language comprehension possible? In this work, we extend past work on algorithmic models of noisy-channel inference to model intercomprehension in a Bayesian framework. The model uses an LM in L1 only for scoring latent hypotheses about the translations of observed L2 utterances, and a general-purpose noise model to infer a mapping between L2 and L1 words based on either form-based similarity or symbolic rules. We then conduct a human behavioral experiment, eliciting inferences for utterances in Dutch, Italian, and Ukrainian from speakers of English, Spanish, and Russian, respectively. Our full model shows a closer alignment to the distribution of human intercomprehension performance than ablations, and also compares favorably to zero-shot prompting of much larger models. These results provide a cognitively plausible computational model of intercomprehension, and highlight the flexible inferences made by comprehenders under wide uncertainty in real-world cross-language scenarios. We share our code publicly.

Token-reduction tools for coding agents are often evaluated by the number of tokens they remove, but token count alone does not determine end-to-end inference cost. We evaluate three token-reduction approaches against an unmodified Claude Code baseline across controlled coding tasks, measuring provider-billed cost, task success, cache traffic, and agent behavior. The largest compression setup reduced delivered tool-output tokens by 38.4% but increased billed cost by 6.8%, while lighter compression produced only small and statistically uncertain savings. Across tasks, token reduction was weakly correlated with cost reduction (Pearson r = 0.15). Cost decomposition shows that prompt-cache creation and reads dominate the measured input-side cost, leaving only a limited fraction of total spend directly addressable by tool-output compression. We also find that compression can alter agent trajectories through additional retrieval, diagnosis, testing, and turns, offsetting local token savings. On a SWE-bench Go subset, aggressive compression also reduced successful patch application. These results show that token reduction is not a reliable proxy for cost reduction in tool-heavy coding agents. Effective optimization should therefore be evaluated at the level of cost per successful task, including cache behavior, trajectory changes, and correctness rather than token counts alone.

Recent LLM-based multi-agent urban simulators can generate semantically rich city routines, but they remain costly to scale and are often weakly validated against empirical mobility patterns. We present CityBehavEx, an interactive LLM-assisted urban simulation platform that scales to city-size populations, exposes agent behavior for inspection, supports empirical validation, and generates mobility patterns that better match real-world spatial, temporal, and semantic distributions. Instead of invoking large language models for every agent action, CityBehavEx combines established human mobility models with fine-tuned cross-encoders that estimate semantic alignment between agent profiles, schedules, and activity transitions. This design enables large-scale simulations, as demonstrated in a case study of 100,000 agents over 75 days in under one hour on a single consumer GPU. The platform allows users to define simulation regions, launch experiments, inspect trajectories and activity traces, debug unrealistic behaviors, and validate generated routines against real-world mobility, time-use, and semantic metrics.

Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expanded voxel selection (10K->15K), substitution of GPT-2 medium for GPT-1 as the beam-search proposal model, and GPU-accelerated bootstrap training, achieving mean METEOR = 0.149 and BLEU-1 = 0.200 across three held-out narratives for subject UTS03 – an 11% relative METEOR gain over our replication baseline. Second, we introduce fMRIFlamingo, which maps BOLD activity to a frozen Llama-3.2-1B with trainable gated cross-attention layers via a learned brain tokenizer and a Perceiver Resampler. Despite achieving 42.86% Top-1 accuracy on a 1-in-100 ranking task, well above chance, a blind control ablation with zeroed fMRI inputs yields near-identical scores, revealing that apparent decoding success is driven primarily by the frozen language prior rather than by neural input. These results demonstrate that high-capacity language models do not inherently improve fMRI decoding and can actively obscure failures without rigorous blind-control evaluation.

Continuous semantic reconstruction from non-invasive neural recordings remains limited by the representational mismatch between semantic feature spaces and neural coding patterns, which severely impedes cross-modal alignment between high-noise neural signals and target semantic features. Prior semantic decoders have predominantly relied on static lexical representations or dynamic contextualized representations in isolation. This single-dimension approach inevitably leads to severe information loss, as it fails to account for the human brain's capacity to integrate stable word attributes and dynamic contexts simultaneously. To bridge this gap, this study introduces a multi-feature fusion framework for non-invasive semantic reconstruction, systematically benchmarking two integration approaches: linear Naive Concatenation and non-linear Multi-Head Cross-Attention. Within this framework, our approach complements static lexical representations (W2V) with dynamic contextual representations (GPT) via an interactive gating mechanism to facilitate cooperative processing during language comprehension. Evaluated through extensive semantic reconstruction and text generation experiments, our framework reveals a robust performance hierarchy: Cross-Att > Concat > GPT > W2V. Crucially, the non-linear cross-attention fusion method achieves state-of-the-art performance, demonstrating that neural language decoding benefits from simulating the collaborative modulation between contextual information and core lexical attributes rather than depending on isolated individual features, while also offering a viable non-invasive brain-to-text decoding method.

Large language models (LLMs) are increasingly being explored for clinical decision support, but their reliability in complex oncology treatment planning remains unclear. We evaluated agentic LLM systems for breast cancer treatment recommendation generation using 72 real clinical cases across stages I to IV and 1,147 case-specific rubrics generated through Asymmetric Information Rubric Generation (AIRG), in which the rubric generator had access to real clinical decisions unavailable to the evaluated models. Seven pipelines were compared, including single-LLM baselines, tool-augmented systems, and multi-agent architectures with fact checking and autonomous subagent spawning. The best-performing configuration, Claude Opus 4.8 with the D&C+SA pipeline, achieved a global score of 0.594 $\pm$ 0.025. Tool use and increased agent autonomy had mixed effects, improving performance in some settings but degrading it in others. Performance varied by clinical domain and disease stage, and oncologist-led error analysis revealed persistent clinically relevant failures, including incorrect or missing recommendations, flawed justifications, citation errors, outdated claims, and overconfidence. These findings suggest that agentic LLM systems can generate clinically relevant breast cancer recommendations, but remain insufficient for unsupervised clinical use.

Deploying medical visual question answering (MedVQA) systems in real-world clinical settings requires models that adapt to new clinical tasks without forgetting previously acquired knowledge. Continual learning (CL) provides a practical framework for this setting. Despite rapid progress in medical vision-language models, the behavior of CL methods when training these models across heterogeneous MedVQA tasks remains underexplored. This work presents a systematic evaluation of CL for MedVQA across diverse clinical objectives, including classification, multi-label classification, detection, cell counting, and report generation. Specifically, we explore (1) the ability of existing CL methods to mitigate catastrophic forgetting; (2) their sensitivity to task ordering, analyzing how different task sequences influence performance retention and forgetting; and (3) the evolution of low-rank adaptation parameters as new tasks are learned, revealing patterns of weight drift under different CL methods. Our findings suggest that existing CL methods struggle to maintain stability-plasticity balance when tasks with different objectives and supervision formats are interleaved. Code and full experimental setup will be publicly available.

Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream. We examine whether the activation of an FFN neuron can be explained by a sparse set of preceding neuron activations and attention outputs. We introduce a training-free attribution method that estimates the relative influence of upstream neurons and attention outputs on a target neuron's activation. Empirically, across models and layers, we find that small subsets of preceding activations and attention outputs suffice to preserve neuron activations with high fidelity when all remaining inputs are masked with their average values. Effective sparsity is even greater when accounting for the inherent activation sparsity of upstream layers. Moreover, applying the neuron-specific masks in all layers simultaneously, such that the induced deviations propagate through the network, leaves model perplexity largely unchanged at moderate sparsity levels. These results demonstrate that, despite dense parameterization, FFNs exhibit sparse and structured inter-layer dependencies at the neuron level. Our method provides a practical, scalable tool for circuit-level interpretability and identifies candidate sparse pathways with potential implications for efficient inference.

Aggregate reliability estimates can obscure heterogeneity in measurement-design burden across response conditions, so a single G- or D-study may mischaracterize a design's adequacy for particular strata. This study introduces a conditional generalizability framework with three components. First, automated scoring configurations – the encoder architectures and scoring-head families admissible within a fixed pipeline – are treated as a universe of admissible measurement conditions rather than incidental modeling choices. Second, analytical D-study projections are compared with empirical configuration sweeps over a finite scoring pool, yielding two estimands of design adequacy whose agreement or divergence diagnoses the realized configuration universe. Third, evidence is conditioned on entropy-defined response strata, treating entropy as an operational stratification variable, not a construct claim about writing quality. Whereas recent generalizability-theory extensions address AI-generated item variants on the response side, this framework addresses the analogous scoring-side problem: AI-mediated scoring configurations. Demonstrated with automated essay scoring of timed L2 writing, the realized design was dependable in aggregate (Phi approx 0.76). Re-estimated within entropy strata, dependability stayed high but declined modestly and robustly (Phi = 0.88, 0.87, 0.84) – a gradient implying different decision-study requirements, the highest-entropy stratum requiring the most crossed conditions. The framework offers a portable workflow for evaluating nonuniform dependability.

In 2019, OpenAI released two million GPT-2 outputs-ungrammatical, half broken-to aid the detection of machine-generated text. The alignment that produced their more fluent successors is usually regarded as an engineering achievement; we read it instead as the newest expression of optimization culture: the conviction, older than the technology, that measurable improvement along predefined axes exhausts the question of value. Tracing that conviction through the stack-pretraining, decoding, preference tuning, benchmarking, interface-and back through its genealogy in the audit society, we arrive at the limit: an optimization procedure can measure how improbable a piece of generated text is; it cannot tell whether that unlikelihood is error or invention. A procedure that cannot make that distinction has nonetheless, within half a decade, assumed the authority to set the protocols of legitimate language. Held for centuries by academies and schoolrooms, grammars and examiners, this authority has been given over to loss functions, reward models, benchmarks, and system prompts: an apparatus that executes the office of judgment with no capacity for judging.

Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone of capable, transparent AI systems. Yet while LLMs have made significant progress across diverse real-world tasks, it is not yet clear when, how, or to what extent they can exhibit or be endowed with effective metacognitive abilities, nor how such abilities can be adapted to advance the fundamental capabilities, reliability, and intelligence of AI systems. This paper bridges this gap by presenting the first comprehensive overview of the current state of knowledge on metacognition for LLMs. We analyze and taxonomize the landscape of this emerging field and summarize recent technical advancements, including methods and benchmarks to measure and evaluate LLMs' metacognitive abilities, techniques to elicit, improve, and apply metacognition in LLMs, and findings and implications of ongoing research. We also discuss applications, open questions and challenges, and promising directions for future work. Our aim is to provide a detailed and up-to-date review of this topic and stimulate meaningful research and discussion. An organized list of papers can be found at https://github.com/yale-nlp/LLM-Metacognition.

Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross-validation, and a held-out evaluation on a Spanish institutional corpus with a frozen-encoder design. Two questions limit its reuse: whether a protocol fixed to 2019-era frozen embeddings stays competitive as representation methods advance, and whether it transfers to a second language. We re-run it on the original Spanish data across three representation generations, sparse lexical features, frozen transformer embeddings, and prompted large language models, and transfer its sentiment task to English with a balanced 45,000-comment corpus checked against an aspect-labeled education dataset. Treating paired comparisons as descriptive, we find the protocol durable: a 2026 frontier model posts the highest thematic F1 on the hardest Spanish task, yet shows no sentiment advantage over a cheap model and no descriptive separation from it on English, so model choice is a deployment decision, not a property of the method.

Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-output view and operationally useful in ways it does not afford. We report three findings, across seven judges, seven bias types, and nine benchmarks. Geometry: baseline judging inputs occupy a tight activation manifold while biased inputs are displaced along a low-dimensional, type-specific subspace that sharpens with depth and is recovered consistently by three families of estimators. Causal control: steering hidden states along this subspace drives scoring in both directions, forward shifts reproducing biased scoring on clean inputs and reverse shifts restoring baseline scoring on biased ones, while matched-norm random directions produce shifts an order of magnitude smaller. Operational: a simple linear projection onto the same bias-direction features anticipates judge failures on three entirely unseen benchmarks, substantially outperforming text-based alternatives. Reading bias as activation geometry, rather than as input-output noise, unifies geometric structure, causal control, and operational prediction within a single framework. The project page is available at https://xzx34.github.io/unfair-judge/

Large language models (LLMs) have achieved remarkable performance on high-school and competition-level mathematics, yet their capabilities on advanced mathematics remain poorly understood. Existing benchmarks, however, fall short in both scope and evaluation granularity: they provide limited disciplinary coverage and often rely on final-answer correctness or coarse judgments, leaving the validity of the reasoning process inadequately assessed. To bridge this gap, we introduce AdvancedMathBench, a benchmark suite designed to evaluate the reasoning capabilities of LLMs on advanced mathematical proofs. Its core generation benchmark, ProverBench, contains 245 problems spanning undergraduate (UG) and doctoral qualifying-exam (QE) levels. To reliably evaluate these proofs, we develop a dedicated automatic verification pipeline that is trained on large-scale expert annotations, produces both correctness verdicts and fine-grained analyses, and exhibits strong agreement with human experts on held-out proof trajectories. We further introduce VerifierBench, consisting of 888 model-generated proof trajectories paired with expert ground truth, to evaluate whether models can correctly judge proof validity and provide sound verification rationales. Experiments show that AdvancedMathBench remains challenging for frontier models. On proof generation, the best-performing model, GPT-5.5-xhigh, achieves only 64.5 and 48.9 on the UG and QE splits, respectively. On proof verification, the best model only attains a Balanced F1 of 65.1. Further analysis reveals a notable mismatch between proof generation and verification capabilities across models.

This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography. While generative AI offers significant opportunities to enhance lexicographic work, it also raises concerns regarding the future role of lexicographers and the preservation of linguistic and cultural diversity. Drawing on HCAI principles and previous applications in other language professions, the paper identifies four interrelated dimensions through which AI integration in lexicography can be understood and critically examined: the augmented lexicographer, the sociotechnical context of AI integration, bias, and the design of AI-powered lexicographic tools. The framework argues that AI should augment rather than replace lexicographers, combining automation with meaningful human control. It further emphasizes the importance of preserving professional agency, mitigating AI-generated biases, and designing tools around the needs of lexicographers. By doing so, the paper provides a foundation for future research and the beneficial integration of AI into lexicographic workflows.

Shared meaning in language requires people to learn and agree on categories. We ask how characteristics of agents' memories change the emergence and evolution of shared meaning. Without a coordination game, models of conceptual semantics cannot explain how shared meaning emerges and changes in groups of people; however, existing games assume that players share payoffs in a partnership setting. We model conceptual alignment as a non-partnership game and illustrate differences in actual and perceived conceptual convergence from counterfactual simulations using agents with varying levels of adaptiveness and memory degradation. We found that adaptive players achieved actual convergence faster and had closer final conceptual regions than non-adaptive players, while non-adaptive players perceived convergence earlier. Weighing novel information less over time resulted in more stable agreements than fixing the weight of novel information. Memory features are critical to the emergence and evolution of actual and perceived convergence.

Retrieval-Augmented Generation (RAG) has been increasingly adopted to reduce hallucinations and strengthen the factual grounding of large language models (LLMs). While robustness to errors in the retrieval process has been explored, the impact of ideological bias on LLM outputs has been overlooked. For instance, if the retrieved material contains ideological positions, the RAG may transmit, amplify, or suppress such ideological discourses in its outputs. In this study, we address this issue by examining the influence of the RAG framework, comprising ideological discourses, in LLM-generated answers. To this end, we applied Lexical Multidimensional Analysis (LMDA) on a corpus of 1,117 COVID-19 treatment articles, identifying three ideological discourses. This corpus is then used as the external knowledge source for the RAG. We assessed several LLMs by having the models answer ideological questions at different sampling temperatures. The generated texts were assessed semantically and lexically based on their similarities with ideological reference texts. Our findings show that the RAG framework is prone to transferring ideological discourses into LLM responses, with sampling temperature having a measurable impact on the strength of this transfer. Discoursive alignment between generated answers and the reference text is highest at moderate temperatures, where models balance stochasticity with retrieval grounding, and drops at low temperatures, indicating that overly deterministic sampling suppresses discourse transfer.

A theoretical understanding of Transformers is crucial to better understand the capacities and limitations of large language models (LLMs). There is much work analyzing the expressivity of attention-based models. By proposing handcrafted weights or using computational complexity arguments, a large amount of past theoretical works have sought to characterize which tasks are and which are not in the hypothesis class of Transformer models. However, little work investigates the learnability of such solutions. In this work, we make progress towards this goal. Inspired by recent loss landscape analysis work, we propose preliminary sample complexity bounds for learning C-RASP constructions with Transformers.