Introduces CHARM framework that detects cascading hallucinations in agentic RAG at 89.4% rate with 5.3% false positives and reduces error propagation by 82.1% on multi-hop QA benchmarks.
hub
Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies
21 Pith papers cite this work, alongside 24 external citations. Polarity classification is still indexing.
21
Pith papers citing it
24
external citations · external index
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
Introduces AVTrack dataset for audio-visual tracking in challenging human-centric scenes, demonstrating performance drops in existing methods.
HIDBench unifies DARPA-E3, DARPA-E5, and NodLink datasets with a data pipeline to benchmark LLMs for host-based intrusion detection, showing high precision on simple logs but sharp drops in MCC and rises in false positives on complex noisy data.
In 30-step recursive LLM loops, append-mode persistent escape from source basins reaches 50% near 400 tokens under full history but plateaus below 50% under tail-clip memory policy, while replace-mode switching largely reflects state reset.
C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.
Hallucinations are inevitable in LLMs because they cannot learn all computable functions according to learning theory.
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.
Internal probes across three model families fail generalization and specificity tests and therefore do not support robust pre-action misalignment monitoring.
AutoBG is a multi-module AI assistant that uses critic-driven iterative refinement on LLM-generated rulebooks, trained on 2.2K rulebooks and 180K reviews, to produce audience-tested designs that outperform GPT-5.4 baselines.
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
Position and step penalty plus visual reasoning guidance fix premature answering and weak visual grounding in diffusion MLLMs, delivering up to 7.5% accuracy gains and over 3x speedup.
FVRuleLearner retrieves learned operator-level reasoning rules to boost the functional correctness of LLM-generated SystemVerilog assertions by roughly 30 percentage points over simple prompting baselines.
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
FLy is a training-free method that speeds up LLM generation by accepting semantically correct but non-exact draft tokens via an entropy gate and deferred verification window.
ORCA is an agentic reasoning framework that enhances factual accuracy and adversarial robustness of pretrained LVLMs via an Observe-Reason-Critique-Act loop with small vision models, reporting accuracy gains of up to 40% on hallucination benchmarks and 20% under adversarial perturbations.
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
LLMs cannot reliably self-correct reasoning mistakes using only their internal capabilities and often degrade in performance without external feedback.
TSGuard builds domain knowledge bases offline from historical incidents and applies online multi-agent structured reasoning to diagnose AI workload failures, delivering 19.8% higher accuracy and 63.4% lower verification time than baselines on Azure production data.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Introduces CHARM framework that detects cascading hallucinations in agentic RAG at 89.4% rate with 5.3% false positives and reduces error propagation by 82.1% on multi-hop QA benchmarks.
-
AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes
Introduces AVTrack dataset for audio-visual tracking in challenging human-centric scenes, demonstrating performance drops in existing methods.
-
HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection
HIDBench unifies DARPA-E3, DARPA-E5, and NodLink datasets with a data pipeline to benchmark LLMs for host-based intrusion detection, showing high precision on simple logs but sharp drops in MCC and rises in false positives on complex noisy data.
-
Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
In 30-step recursive LLM loops, append-mode persistent escape from source basins reaches 50% near 400 tokens under full history but plateaus below 50% under tail-clip memory policy, while replace-mode switching largely reflects state reset.
-
C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving
C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.
-
Hallucination is Inevitable: An Innate Limitation of Large Language Models
Hallucinations are inevitable in LLMs because they cannot learn all computable functions according to learning theory.
-
Self-Rewarding Language Models
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
-
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.
-
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring
Internal probes across three model families fail generalization and specificity tests and therefore do not support robust pre-action misalignment monitoring.
-
AutoBG: A Board Game Design Assistant with Interactive Ideation, Iterative Rulebook Generation, and Individualized Feedback
AutoBG is a multi-module AI assistant that uses critic-driven iterative refinement on LLM-generated rulebooks, trained on 2.2K rulebooks and 180K reviews, to produce audience-tested designs that outperform GPT-5.4 baselines.
-
AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
-
Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
Position and step penalty plus visual reasoning guidance fix premature answering and weak visual grounding in diffusion MLLMs, delivering up to 7.5% accuracy gains and over 3x speedup.
-
FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification
FVRuleLearner retrieves learned operator-level reasoning rules to boost the functional correctness of LLM-generated SystemVerilog assertions by roughly 30 percentage points over simple prompting baselines.
-
A Minimal Agent for Automated Theorem Proving
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
-
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
FLy is a training-free method that speeds up LLM generation by accepting semantically correct but non-exact draft tokens via an entropy gate and deferred verification window.
-
ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models
ORCA is an agentic reasoning framework that enhances factual accuracy and adversarial robustness of pretrained LVLMs via an Observe-Reason-Critique-Act loop with small vision models, reporting accuracy gains of up to 40% on hallucination benchmarks and 20% under adversarial perturbations.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
Large Language Models Cannot Self-Correct Reasoning Yet
LLMs cannot reliably self-correct reasoning mistakes using only their internal capabilities and often degrade in performance without external feedback.
-
TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud
TSGuard builds domain knowledge bases offline from historical incidents and applies online multi-agent structured reasoning to diagnose AI workload failures, delivering 19.8% higher accuracy and 63.4% lower verification time than baselines on Azure production data.
-
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.
-
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.