Entities · Models
gpt-4o-mini
46 articles tagged with this entity.
-
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
-
Co-LMLM: Continuous-Query Limited Memory Language Models
-
What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study
-
A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements
-
Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents
-
Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations
-
Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges
-
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
-
Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike
-
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
-
From Detection to Action: Using LLM Agents for Fault-Tolerant Control
-
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
-
CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
-
T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph
-
Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability
-
Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
-
LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks
-
Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars
-
In-Context Environments Induce Evaluation-Awareness in Language Models
-
Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction
-
The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation
-
RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning
-
Deployment-Time Memorization in Foundation-Model Agents
-
Capacity, Not Format: Rethinking Structured Reasoning Failures
-
Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals
-
Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling
-
StreamingVLM: Real-Time Understanding for Infinite Video Streams
-
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
-
OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources
-
SDR: Set-Distance Rewards for Radiology Report Generation
-
Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution
-
How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency
-
Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles
-
Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning
-
Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models
-
Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
-
Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Gender Recoverability
-
Reliable Extraction of Clinical Follow-Up Instructions: A Hybrid Neural-Symbolic Pipeline
-
Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
-
Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection
-
Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content
-
Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations
-
Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
-
Beyond Public Access in LLM Pre-Training Data
-
Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation
-
CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams