Sequential LLM defense deployment leads to risk exacerbation in 38.9% of cases due to anti-aligned updates in shared critical layers, addressed by conflict-guided layer freezing.
hub
Trustllm: Trustworthiness in large language models.arXiv preprint arXiv:2401.05561
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 1
other 1
citation-polarity summary
representative citing papers
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
AVID is the first large-scale benchmark for audio-visual inconsistency detection, grounding, classification, and reasoning in long videos, constructed via agent-driven methods and showing that state-of-the-art models struggle while a fine-tuned baseline improves performance.
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains while creating tail risks.
LLM agents can reconstruct high-fidelity personal profiles from minimal PII seeds with over 90% accuracy in under 10 minutes at less than $3 cost, exposing three escalating tiers of privacy risks.
PIA achieves lower attack success rates on persona-based jailbreaks via self-play co-evolution of attacks (PLE) and defenses (PICL) that structurally decouples safety from persona context using unilateral KL-divergence.
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
BAR trains independent domain experts via separate mid-training, SFT, and RL pipelines then composes them with a MoE router to match monolithic retraining performance at lower cost and without catastrophic forgetting.
CoT compression frequently introduces trustworthiness regressions with method-specific degradation profiles; a proposed normalized efficiency score and alignment-aware DPO variant reduce length by 19.3% with smaller trustworthiness loss.
OutSafe-Bench supplies the first large-scale four-modality safety dataset and evaluation framework that exposes persistent unsafe outputs in nine leading multimodal LLMs.
JailbreakBench supplies an evolving set of jailbreak prompts, a 100-behavior dataset aligned with usage policies, a standardized evaluation framework, and a leaderboard to enable comparable assessments of attacks and defenses on LLMs.
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.
A multi-dimensional audit framework for politically aligned LLMs finds consistent trade-offs: larger models are more effective and truthful but less fair with higher bias, while fine-tuned models reduce bias but increase hallucinations and reasoning decline, and all tested models show deficiencies.
Vibe Medicine proposes directing AI agents via natural language for end-to-end biomedical workflows using LLMs, agent frameworks, and a curated collection of over 1,000 medical skills.
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
citing papers explorer
-
Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models
Sequential LLM defense deployment leads to risk exacerbation in 38.9% of cases due to anti-aligned updates in shared critical layers, addressed by conflict-guided layer freezing.
-
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
-
AVID: A Benchmark for Omni-Modal Audio-Visual Inconsistency Understanding via Agent-Driven Construction
AVID is the first large-scale benchmark for audio-visual inconsistency detection, grounding, classification, and reasoning in long videos, constructed via agent-driven methods and showing that state-of-the-art models struggle while a fine-tuned baseline improves performance.
-
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains while creating tail risks.
-
Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
LLM agents can reconstruct high-fidelity personal profiles from minimal PII seeds with over 90% accuracy in under 10 minutes at less than $3 cost, exposing three escalating tiers of privacy risks.
-
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
PIA achieves lower attack success rates on persona-based jailbreaks via self-play co-evolution of attacks (PLE) and defenses (PICL) that structurally decouples safety from persona context using unilateral KL-divergence.
-
Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
-
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
BAR trains independent domain experts via separate mid-training, SFT, and RL pipelines then composes them with a MoE router to match monolithic retraining performance at lower cost and without catastrophic forgetting.
-
Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression
CoT compression frequently introduces trustworthiness regressions with method-specific degradation profiles; a proposed normalized efficiency score and alignment-aware DPO variant reduce length by 19.3% with smaller trustworthiness loss.
-
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
OutSafe-Bench supplies the first large-scale four-modality safety dataset and evaluation framework that exposes persistent unsafe outputs in nine leading multimodal LLMs.
-
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
JailbreakBench supplies an evolving set of jailbreak prompts, a 100-behavior dataset aligned with usage policies, a standardized evaluation framework, and a leaderboard to enable comparable assessments of attacks and defenses on LLMs.
-
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
-
Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.
-
A Multi-Dimensional Audit of Politically Aligned Large Language Models
A multi-dimensional audit framework for politically aligned LLMs finds consistent trade-offs: larger models are more effective and truthful but less fair with higher bias, while fine-tuned models reduce bias but increase hallucinations and reasoning decline, and all tested models show deficiencies.
-
Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work
Vibe Medicine proposes directing AI agents via natural language for end-to-end biomedical workflows using LLMs, agent frameworks, and a curated collection of over 1,000 medical skills.
-
Large Language Models: A Survey
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.