All Practice Areas

Intellectual Property

지적재산권

Jurisdiction: All US KR EU Intl
LOW Academic International

Web Verbs: Typed Abstractions for Reliable Task Composition on the Agentic Web

arXiv:2602.17245v1 Announce Type: new Abstract: The Web is evolving from a medium that humans browse to an environment where software agents act on behalf of users. Advances in large language models (LLMs) make natural language a practical interface for goal-directed...

1 min 2 months ago
nda
LOW Academic International

Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect

arXiv:2602.16852v1 Announce Type: new Abstract: Meenzerisch, the dialect spoken in the German city of Mainz, is also the traditional language of the Mainz carnival, a yearly celebration well known throughout Germany. However, Meenzerisch is on the verge of dying out-a...

1 min 2 months ago
nda
LOW Academic International

Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History

arXiv:2602.17003v1 Announce Type: new Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring user...

1 min 2 months ago
ip
LOW Academic International

ReIn: Conversational Error Recovery with Reasoning Inception

arXiv:2602.17022v1 Announce Type: new Abstract: Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on error prevention, this work focuses...

1 min 2 months ago
ip
LOW Academic International

Large Language Models Persuade Without Planning Theory of Mind

arXiv:2602.17045v1 Announce Type: new Abstract: A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interactive question-and-answer benchmarks. However, theoretical work in the field suggests that first-personal...

1 min 2 months ago
ip
LOW Academic International

ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning

arXiv:2602.17054v1 Announce Type: new Abstract: While recent Arabic NLP benchmarks focus on scale, they often rely on synthetic or translated data which may benefit from deeper linguistic verification. We introduce ALPS (Arabic Linguistic & Pragmatic Suite), a native, expert-curated diagnostic...

1 min 2 months ago
nda
LOW Academic International

The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI

arXiv:2602.17127v1 Announce Type: new Abstract: As Large Language Models (LLMs) transition from standalone chat interfaces to foundational reasoning layers in multi-agent systems and recursive evaluation loops (LLM-as-a-judge), the detection of durable, provider-level behavioral signatures becomes a critical requirement for safety...

1 min 2 months ago
nda
LOW Academic International

Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study

arXiv:2602.17262v1 Announce Type: new Abstract: Human self-report questionnaires are increasingly used in NLP to benchmark and audit large language models (LLMs), from persona consistency to safety and bias assessments. Yet these instruments presume honest responding; in evaluative contexts, LLMs can...

1 min 2 months ago
nda
LOW News International

OpenAI debated calling police about suspected Canadian shooter’s chats

Jesse Van Rootselaar's descriptions of gun violence were flagged by tools that monitor ChatGPT for misuse.

1 min 2 months ago
ip
LOW Academic International

RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering

arXiv:2602.17366v1 Announce Type: new Abstract: Long-tail question answering presents significant challenges for large language models (LLMs) due to their limited ability to acquire and accurately recall less common knowledge. Retrieval-augmented generation (RAG) systems have shown great promise in mitigating this...

1 min 2 months ago
ip
LOW Academic International

Diverse Word Choices, Same Reference: Annotating Lexically-Rich Cross-Document Coreference

arXiv:2602.17424v1 Announce Type: new Abstract: Cross-document coreference resolution (CDCR) identifies and links mentions of the same entities and events across related documents, enabling content analysis that aggregates information at the level of discourse participants. However, existing datasets primarily focus on...

1 min 2 months ago
ip
LOW Academic International

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

arXiv:2602.17431v1 Announce Type: new Abstract: Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generalize well to long-form generation. We introduce a taxonomy...

1 min 2 months ago
ip
LOW Academic International

PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions

arXiv:2602.17467v1 Announce Type: new Abstract: The increasing volume of hate speech on online platforms poses significant societal challenges. While the Natural Language Processing community has developed effective methods to automatically detect the presence of hate speech, responses to it, called...

1 min 2 months ago
ip
LOW Academic International

Modeling Distinct Human Interaction in Web Agents

arXiv:2602.17588v1 Announce Type: new Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene,...

1 min 2 months ago
ip
LOW Academic International

The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?

arXiv:2602.17598v1 Announce Type: new Abstract: Current speech LLMs largely perform implicit ASR: on tasks solvable from a transcript, they are behaviorally and mechanistically equivalent to simple Whisper$\to$LLM cascades. We show this through matched-backbone testing across four speech LLMs and six...

1 min 2 months ago
ip
LOW Academic International

Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking

arXiv:2602.17653v1 Announce Type: new Abstract: Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order. In this paper, we...

1 min 2 months ago
licensing
LOW Academic International

Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency

arXiv:2602.16787v1 Announce Type: cross Abstract: Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in their causal reasoning ability. While recent work has demonstrated that labeled counterfactual tasks...

1 min 2 months ago
ip
LOW Academic International

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

arXiv:2602.16819v1 Announce Type: cross Abstract: When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more various and complex tasks that involve other...

1 min 2 months ago
ip
LOW Academic International

Quantifying LLM Attention-Head Stability: Implications for Circuit Universality

arXiv:2602.16740v1 Announce Type: new Abstract: In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their stability across different instances...

1 min 2 months ago
nda
LOW Academic International

PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency

arXiv:2602.16745v1 Announce Type: new Abstract: Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited budget remains an open challenge. We introduce PETS (Principled and Efficient Test-TimeSelf-Consistency), which initiates a principled...

1 min 2 months ago
ip
LOW Academic International

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking

arXiv:2602.16746v1 Announce Type: new Abstract: Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of attention weight...

1 min 2 months ago
ip
LOW Academic International

Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models

arXiv:2602.16793v1 Announce Type: new Abstract: In the past year, custom and unreleased math reasoning models reached gold medal performance on the International Mathematical Olympiad (IMO). Similar performance was then reported using large-scale inference on publicly available models but at prohibitive...

1 min 2 months ago
ip
LOW Academic International

HiVAE: Hierarchical Latent Variables for Scalable Theory of Mind

arXiv:2602.16826v1 Announce Type: new Abstract: Theory of mind (ToM) enables AI systems to infer agents' hidden goals and mental states, but existing approaches focus mainly on small human understandable gridworld spaces. We introduce HiVAE, a hierarchical variational architecture that scales...

1 min 2 months ago
nda
LOW Academic International

VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study

arXiv:2602.16833v1 Announce Type: new Abstract: Exploration remains a key bottleneck for reinforcement learning (RL) post-training of large language models (LLMs), where sparse feedback and large action spaces can lead to premature collapse into repetitive behaviors. We propose Verbalized Action Masking...

1 min 2 months ago
ip
LOW Academic International

Multi-Agent Lipschitz Bandits

arXiv:2602.16965v1 Announce Type: new Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward. Our objective is to design a communication-free policy that maximizes collective reward, with coordination costs...

1 min 2 months ago
ip
LOW Academic International

A Unified Framework for Locality in Scalable MARL

arXiv:2602.16966v1 Announce Type: new Abstract: Scalable Multi-Agent Reinforcement Learning (MARL) is fundamentally challenged by the curse of dimensionality. A common solution is to exploit locality, which hinges on an Exponential Decay Property (EDP) of the value function. However, existing conditions...

1 min 2 months ago
nda
LOW Academic International

Discovering Universal Activation Directions for PII Leakage in Language Models

arXiv:2602.16980v1 Announce Type: new Abstract: Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability...

1 min 2 months ago
ip
LOW Academic International

Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning

arXiv:2602.17009v1 Announce Type: new Abstract: Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on good individual actions, but on selecting compatible actions across agents to synchronize behavior,...

1 min 2 months ago
nda
LOW Academic International

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

arXiv:2602.17025v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled trajectories, extended deliberation can create more chances to realize...

1 min 2 months ago
nda
LOW Academic International

MeGU: Machine-Guided Unlearning with Target Feature Disentanglement

arXiv:2602.17088v1 Announce Type: new Abstract: The growing concern over training data privacy has elevated the "Right to be Forgotten" into a critical requirement, thereby raising the demand for effective Machine Unlearning. However, existing unlearning approaches commonly suffer from a fundamental...

1 min 2 months ago
nda
Previous Page 67 of 70 Next

Impact Distribution

Critical 0
High 2
Medium 37
Low 3752