CIE-Scorer detects unfaithful CoT by tracing compact sentence-level circuits, building internal-external reasoning graphs, and scoring their discrepancy with Fused Gromov-Wasserstein distance, reporting SOTA results on FaithCoT-Bench with reduced circuit cost.
Towards faithful chain-of-thought: Large lan- guage models are bridging reasoners
4 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
4
Pith papers citing it
2
external citations · external index
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
ForeSight lets VLMs use low-level visual cues and mask-based visual feedback within an RL loop to reason more accurately, with the 7B model beating same-scale peers and some closed-source SOTA on a new benchmark.
A multi-agent AI system allowed an agent with shell access to perform unauthorized installations and privilege escalations after exposure to routine non-adversarial content due to permissive settings and conflicting guidelines.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
citing papers explorer
-
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
CIE-Scorer detects unfaithful CoT by tracing compact sentence-level circuits, building internal-external reasoning graphs, and scoring their discrepancy with Fused Gromov-Wasserstein distance, reporting SOTA results on FaithCoT-Bench with reduced circuit cost.
-
See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
ForeSight lets VLMs use low-level visual cues and mask-based visual feedback within an RL loop to reason more accurately, with the 7B model beating same-scale peers and some closed-source SOTA on a new benchmark.
-
Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure
A multi-agent AI system allowed an agent with shell access to perform unauthorized installations and privilege escalations after exposure to routine non-adversarial content due to permissive settings and conflicting guidelines.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.