Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence
arXiv:2602.12811v1 Announce Type: new Abstract: When humans and large language models (LLMs) process the same text, activations in the LLMs correlate with brain activity measured, e.g., with functional magnetic resonance imaging (fMRI). Moreover, it has been shown that, as the...
ProbeLLM: Automating Principled Diagnosis of LLM Failures
arXiv:2602.12966v1 Announce Type: new Abstract: Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall behind. While automated probing has been enabled by dynamic test generation, existing approaches...
Sparse Autoencoders are Capable LLM Jailbreak Mitigators
arXiv:2602.12418v1 Announce Type: cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with...
HyperMLP: An Integrated Perspective for Sequence Modeling
arXiv:2602.12601v1 Announce Type: cross Abstract: Self-attention is often viewed as probabilistic query-key lookup, motivating designs that preserve normalized attention scores and fixed positional semantics. We advocate a simpler and more unified perspective: an autoregressive attention head can be viewed as...
Abstractive Red-Teaming of Language Model Character
arXiv:2602.12318v1 Announce Type: new Abstract: We want language model assistants to conform to a character specification, which asserts how the model should act across diverse user interactions. While models typically follow these character specifications, they can occasionally violate them in...
Computationally sufficient statistics for Ising models
arXiv:2602.12449v1 Announce Type: new Abstract: Learning Gibbs distributions using only sufficient statistics has long been recognized as a computationally hard problem. On the other hand, computationally efficient algorithms for learning Gibbs distributions rely on access to full sample configurations generated...
Continuous Diffusion Models Can Obey Formal Syntax
arXiv:2602.12468v1 Announce Type: new Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their continuous latent dynamics make discrete constraints -- e.g., the output should be a JSON file that...
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
arXiv:2602.12506v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision language models (VLMs). While RL-tuned VLMs improve on visual reasoning benchmarks, they...
Analytical Results for Two Exponential Family Distributions in Hierarchical Dirichlet Processes
arXiv:2602.12527v1 Announce Type: new Abstract: The Hierarchical Dirichlet Process (HDP) provides a flexible Bayesian nonparametric framework for modeling grouped data with a shared yet unbounded collection of mixture components. While existing applications of the HDP predominantly focus on the Dirichlet-multinomial...
Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models
arXiv:2602.12529v1 Announce Type: new Abstract: Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We introduce Flow-Factory, a unified framework that decouples...
VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
arXiv:2602.12579v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent findings suggest that RLVR primarily functions...
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts - ACL Anthology
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing - ACL Anthology
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track - ACL Anthology
Artificial Intelligence and Law
This journal seeks papers that address the development of formal or computational models of legal knowledge, reasoning, and decision making. It also includes ...
ODW creates business value through website design and development — Osborn Design Works
Osborn Design Works (ODW) designs and develops high-performance websites and apps, leveraging product design, UI/UX design, and marketing design to create business value.
Tech
The latest tech news about the world’s best (and sometimes worst) hardware, apps, and much more. From top companies like Google and Apple to tiny startups vying for your attention, Verge Tech has the latest in what matters in technology...
Headphone Reviews
After the smartphone, headphones are the gadget we reach for most often in our daily lives. Here, The Verge tracks the best headphones for every budget and purpose, whether they be wireless, noise cancelling, in-ear, or over-ear. With all the...
PlayStation
For more than 25 years, Sony’s PlayStation has been synonymous with gaming. It’s given players experiences like God of War, The Last of Us, and Final Fantasy VII alongside technological innovations from CD-ROMs all the way up to 4K, VR,...
India doubles down on state-backed venture capital, approving $1.1B fund
India’s $1.1B fund-of-funds will invest through private VCs to support deep-tech and manufacturing startups.
Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
arXiv:2602.13213v1 Announce Type: new Abstract: Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing. While AI offers substantial efficiency improvements, existing solutions lack comprehensive reasoning capabilities and internal...
A Geometric Taxonomy of Hallucinations in LLMs
arXiv:2602.13224v1 Announce Type: new Abstract: The term "hallucination" in large language models conflates distinct phenomena with different geometric signatures in embedding space. We propose a taxonomy identifying three types: unfaithfulness (failure to engage with provided context), confabulation (invention of semantically...
Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection
arXiv:2602.13226v1 Announce Type: new Abstract: Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection ability. In this...
NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models
arXiv:2602.13237v1 Announce Type: new Abstract: Automated reasoning is critical in domains such as law and governance, where verifying claims against facts in documents requires both accuracy and interpretability. Recent work adopts structured reasoning pipelines that translate natural language into first-order...
TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks
arXiv:2602.13272v1 Announce Type: new Abstract: It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions. We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively...
Artificial Organisations
arXiv:2602.13275v1 Announce Type: new Abstract: Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent AI systems should follow this institutional model...
OpAgent: Operator Agent for Web Navigation
arXiv:2602.13559v1 Announce Type: new Abstract: To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement Learning (RL) using static datasets....
DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solving
arXiv:2602.13616v1 Announce Type: new Abstract: We propose DiffusionRollout, a novel selective rollout planning strategy for autoregressive diffusion models, aimed at mitigating error accumulation in long-horizon predictions of physical systems governed by partial differential equations (PDEs). Building on the recently validated...
Language Model Memory and Memory Models for Language
arXiv:2602.13466v1 Announce Type: new Abstract: The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically...