Analysis of 1.01 million unfiltered Bing queries identifies 18% as geospatial, dominated by transactional categories like costs (15.3%) that exceed traditional GIS scope.
hub
Sentence- BERT : Sentence embeddings using S iamese BERT -networks
63 Pith papers cite this work, alongside 7,637 external citations. Polarity classification is still indexing.
63
Pith papers citing it
7,637
external citations · Crossref
hub tools
co-cited works
representative citing papers
Semantic search retrieves substantially more implicit receptions of Locke's work than lexical baselines in 18th-century corpora, yet remains constrained by lexical gatekeeping.
Test-time scaling for personalized LLMs follows a logarithmic utility curve under oracle selection but standard reward models suffer user-level collapse and query-level hacking; a probabilistic reward model with learned variance enables consistent scaling.
A text-supervised global layout embedding augments local patch representations in late-interaction VDR, yielding +2.4 nDCG@5 and +2.3 MAP@5 gains over ColPali/ColQwen baselines on ViDoRe-v2.
AI-only technical discourse on MoltBook is coherent and organized around 12 themes led by security and trust, but it lacks the concrete code, runtime failures, and reproduction steps common in human GitHub discussions.
CircuitFormer is a 511M-parameter encoder-decoder model that generates analog circuit topologies from text prompts at 100% syntactic correctness and 83% functional success using a new subcircuit-mining tokenizer that keeps vocabulary size fixed at 512.
SkCC compiles LLM skills via SkIR to achieve portability across agent frameworks, reduce adaptation effort from O(m×n) to O(m+n), and enforce security with reported gains in task success rates and token efficiency.
CRAFT is a supervised LLM framework using retrieval-augmented generation, self-refinement, fine-tuning, and preference optimization to create fluent adversarial content that boosts target ranks in neural ranking models, outperforming baselines on MS MARCO and TREC benchmarks with cross-architecture
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
InvEvolve evolves white-box inventory policies from LLMs with statistical safety guarantees and outperforms classical and deep learning methods on synthetic and real retail data.
A cross-cultural survey finds LLM emotional support adoption ranges from 20% to 59% by country, with positive perceptions strongest among higher-SES, religious, married adults aged 25-44 and in English-speaking nations.
R-CAI inverts constitutional AI to automatically generate diverse toxic data for LLM red teaming, with probability clamping improving output coherence by 15% while preserving adversarial strength.
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
Bounded autonomy is a new control architecture that makes LLM characters workable in live multiplayer games by combining interaction stability techniques, action grounding, and lightweight player steering, validated through deployment and analysis.
RAR retrieves candidate items from a 300k-movie corpus then uses LLM generation with RL feedback to produce context-aware recommendations that outperform baselines on benchmarks.
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
LIFT pairs a pre-trained LLM for initial table extraction with a fine-tuned SLM for error repair, matching end-to-end SLM fine-tuning on TEDS while needing only 1,000 examples and gaining robustness.
Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.
Safety Context Injection prepends structured external risk reports via static or agentic analysis to lower attack success rates and toxicity in reasoning models on AdvBench and GPTFuzz benchmarks.
RADAGAS-GPT4o achieves a 22.73% bypass rate against 10 WAFs, succeeding more against AI/ML-based firewalls than rule-based ones.
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
CAR reranks documents in RAG by promoting those that increase generator confidence (via answer consistency sampling) and demoting those that decrease it, yielding NDCG@5 gains on BEIR datasets that correlate with F1 improvements.
A single commercial LLM can cheaply generate large populations of behaviorally equivalent yet structurally diverse malware payloads.
citing papers explorer
-
Much of Geospatial Web Search Is Beyond Traditional GIS
Analysis of 1.01 million unfiltered Bing queries identifies 18% as geospatial, dominated by transactional categories like costs (15.3%) that exceed traditional GIS scope.
-
Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke
Semantic search retrieves substantially more implicit receptions of Locke's work than lexical baselines in 18th-century corpora, yet remains constrained by lexical gatekeeping.
-
Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures
Test-time scaling for personalized LLMs follows a logarithmic utility curve under oracle selection but standard reward models suffer user-level collapse and query-level hacking; a probabilistic reward model with learned variance enables consistent scaling.
-
Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval
A text-supervised global layout embedding augments local patch representations in late-interaction VDR, yielding +2.4 nDCG@5 and +2.3 MAP@5 gains over ColPali/ColQwen baselines on ViDoRe-v2.
-
What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook
AI-only technical discourse on MoltBook is coherent and organized around 12 themes led by security and trust, but it lacks the concrete code, runtime failures, and reproduction steps common in human GitHub discussions.
-
CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt
CircuitFormer is a 511M-parameter encoder-decoder model that generates analog circuit topologies from text prompts at 100% syntactic correctness and 83% functional success using a new subcircuit-mining tokenizer that keeps vocabulary size fixed at 512.
-
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
SkCC compiles LLM skills via SkIR to achieve portability across agent frameworks, reduce adaptation effort from O(m×n) to O(m+n), and enforce security with reported gains in task success rates and token efficiency.
-
Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models
CRAFT is a supervised LLM framework using retrieval-augmented generation, self-refinement, fine-tuning, and preference optimization to create fluent adversarial content that boosts target ranks in neural ranking models, outperforming baselines on MS MARCO and TREC benchmarks with cross-architecture
-
A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
-
InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
InvEvolve evolves white-box inventory policies from LLMs with statistical safety guarantees and outperforms classical and deep learning methods on synthetic and real retail data.
-
From Chatbots to Confidants: A Cross-Cultural Study of LLM Adoption for Emotional Support
A cross-cultural survey finds LLM emotional support adoption ranges from 20% to 59% by country, with positive perceptions strongest among higher-SES, religious, married adults aged 25-44 and in English-speaking nations.
-
Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF
R-CAI inverts constitutional AI to automatically generate diverse toxic data for LLM red teaming, with probability clamping improving output coherence by 15% while preserving adversarial strength.
-
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
-
Bounded Autonomy: Controlling LLM Characters in Live Multiplayer Games
Bounded autonomy is a new control architecture that makes LLM characters workable in live multiplayer games by combining interaction stability techniques, action grounding, and lightweight player steering, validated through deployment and analysis.
-
Retrieval Augmented Conversational Recommendation with Reinforcement Learning
RAR retrieves candidate items from a 300k-movie corpus then uses LLM generation with RL feedback to produce context-aware recommendations that outperform baselines on benchmarks.
-
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
-
LIFT: Last-Mile Fine-Tuning for Table Explicitation
LIFT pairs a pre-trained LLM for initial table extraction with a fine-tuned SLM for error repair, matching end-to-end SLM fine-tuning on TEDS while needing only 1,000 examples and gaining robustness.
-
Task-Adaptive Embedding Refinement via Test-time LLM Guidance
Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.
-
Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
Safety Context Injection prepends structured external risk reports via static or agentic analysis to lower attack success rates and toxicity in reasoning models on AdvBench and GPTFuzz benchmarks.
-
Adversarial SQL Injection Generation with LLM-Based Architectures
RADAGAS-GPT4o achieves a 22.73% bypass rate against 10 WAFs, succeeding more against AI/ML-based firewalls than rule-based ones.
-
SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
-
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
-
CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
CAR reranks documents in RAG by promoting those that increase generator confidence (via answer consistency sampling) and demoting those that decrease it, yielding NDCG@5 gains on BEIR datasets that correlate with F1 improvements.
-
The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code
A single commercial LLM can cheaply generate large populations of behaviorally equivalent yet structurally diverse malware payloads.
-
LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
LEAP adds a layer-wise exit-aware constraint to standard distillation, reconciling it with early-exit mechanisms and delivering 1.61x wall-clock speedup on MiniLM at 0.95 threshold with 91.9% early exits by layer 7.
-
Kernel Affine Hull Machines for Compute-Efficient Query-Side Semantic Encoding
Kernel Affine Hull Machines map lexical features to semantic embeddings via RKHS and least-mean-squares, outperforming adapters in reconstruction and retrieval metrics while reducing latency 8.5-fold on a legal benchmark.
-
Agentic AI for Substance Use Education: Integrating Regulatory and Scientific Knowledge Sources
The authors built and expert-evaluated an agentic AI system integrating DEA regulatory data with dynamic scientific literature via RAG to provide accurate, context-sensitive substance use education, with mean Likert ratings of 4.18-4.35 and substantial rater agreement.
-
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
-
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.
-
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
-
Reducing Maintenance Burden in Behaviour-Driven Development: A Paraphrase-Robust Duplicate-Step Detector with a 1.1M-Step Open Benchmark
A paraphrase-robust duplicate-step detector for Gherkin BDD suites, built on a new 1.1M-step public corpus, reports F1 scores up to 0.906 and estimates 893k eliminable step occurrences corpus-wide.
-
SCURank: Ranking Multiple Candidate Summaries with Summary Content Units for Enhanced Summarization
SCURank ranks multiple summary candidates with Summary Content Units to outperform ROUGE and LLM-based methods in summarization distillation.
-
All Public Voices Are Equal, But Are Some More Equal Than Others to LLMs?
LLMs produce lower-fidelity summaries of identical public comments when attributed to lower-status occupations like street vendors versus financial analysts, with inconsistent race effects and no gender effects.
-
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
-
MetFuse: Figurative Fusion between Metonymy and Metaphor
MetFuse provides the first dataset of 1,000 meaning-aligned quadruplets fusing literal, metonymic, metaphoric, and hybrid sentences, which augments training to boost metonymy and metaphor classification performance on benchmarks.
-
LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces
LAG-XAI treats paraphrasing as affine flows in semantic manifolds using Lie-inspired approximations, achieving AUC 0.7713 on paraphrase detection and 95.3% hallucination detection on HaluEval.
-
Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
-
SemLink: A Semantic-Aware Automated Test Oracle for Hyperlink Verification using Siamese Sentence-BERT
SemLink applies a Siamese SBERT model to detect semantic drift in hyperlinks, achieving 96% recall at 47.5 times the speed of GPT-5.2 using a new 60k-pair dataset.
-
DQA: Diagnostic Question Answering for IT Support
DQA maintains persistent diagnostic state and aggregates retrievals at the root-cause level to reach 78.7% success on 150 enterprise IT scenarios versus 41.3% for standard multi-turn RAG while cutting average turns from 8.4 to 3.9.
-
Align then Train: Efficient Retrieval Adapter Learning
A two-stage adapter method aligns query and document embedding spaces to improve dense retrieval for complex queries using lightweight encoders and few labels.
-
StarCoder 2 and The Stack v2: The Next Generation
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
-
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
REINFORCE-style variants outperform PPO, DPO, and RAFT in RLHF for LLMs by removing unnecessary PPO components and adapting the simpler method to LLM alignment characteristics.
-
Context Convergence Improves Answering Inferential Questions
Passages made from high-convergence sentences improve LLM performance on inferential questions compared to cosine similarity selection.
-
Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
Embeddings reliably capture authorial stylistic features in French literary texts, and these signals persist after LLM rewriting while showing model-specific patterns.
-
Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models
Selective pruning of low-activation neurons in task-specific LLMs preserves accuracy better than random pruning, but removing roughly 10% of highly selective neurons triggers total collapse, with fine-tuning recovering much of the lost performance.
-
Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness
SABA improves LLM performance on detective puzzle benchmarks by recursively fusing information into a base state and using queries to resolve missing premises before concluding.
-
Cross-Model Consistency of AI-Generated Exercise Prescriptions: A Repeated Generation Study Across Three Large Language Models
Three LLMs exhibit distinct consistency profiles in repeated exercise prescription generation, with GPT-4.1 producing unique but semantically stable outputs while Gemini 2.5 Flash achieves high similarity through text duplication.
-
Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
Four attention metrics enable logistic regression classifiers that detect hallucinations in SpeechLLMs with up to +0.23 PR-AUC gains over baselines on ASR and translation tasks.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
-
Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG Systems
The paper introduces a measure of semantic entanglement in embeddings and a pipeline that improves Top-K retrieval precision from 32% to 82% on a healthcare knowledge base.