{"total":11,"items":[{"citing_arxiv_id":"2606.29799","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models","primary_cat":"cs.AI","submitted_at":"2026-06-29T05:27:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CRISTAL is a neurosymbolic framework that synthesizes interpretable probabilistic world models from language priors for full Bayesian analysis and budget-aware data acquisition, claiming Bayes-optimal accuracy on synthetic equity classification with 5 examples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08346","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sanity Checks for Long-Form Hallucination Detection","primary_cat":"cs.CL","submitted_at":"2026-05-08T18:00:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hallucination detectors on LLM reasoning traces often rely on final-answer artifacts rather than reasoning validity; once controlled, lightweight lexical trajectory features suffice for robust detection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07353","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","primary_cat":"cs.AI","submitted_at":"2026-05-08T07:08:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Large reasoning models (LRMs) such as OpenAI-o1 [ 20] and Qwen-3 [ 49] have substantially advanced mathematical and scientific problem-solving through detailed step-by-step generation. However, optimizing these models purely for final-answer correctness masks a critical vulnerability: they frequently arrive at correct conclusions via logically flawed intermediate steps [1]. In high-stakes domains such as medicine and finance [8, 57], relying on invalid reasoning traces poses significant risks. Therefore, reliable LRM deployment demands not only accurate final outputs but verifiably sound reasoning trajectories. The root cause of this vulnerability lies in a fundamental misalignment between a model's internal confidence and logical correctness. In current LRMs, token-level probabilities reflect superficial"},{"citing_arxiv_id":"2605.05777","ref_index":56,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation","primary_cat":"cs.CL","submitted_at":"2026-05-07T07:09:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DisAAD trains a 1%-sized proxy model via adversarial distillation to quantify uncertainty in black-box LLMs by aligning with their output distributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04295","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy","primary_cat":"cs.LG","submitted_at":"2026-05-05T20:56:11+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15109","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation","primary_cat":"cs.CL","submitted_at":"2026-04-16T15:03:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"IUQ quantifies claim-level uncertainty in long-form LLM generation by combining inter-sample consistency and intra-sample faithfulness through an interrogate-then-respond approach and outperforms baselines on two datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07825","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders","primary_cat":"cs.IR","submitted_at":"2026-04-09T05:27:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"if a text was seen during pre-training [ 7, 43, 54, 58]. PDD meth- ods typically rely on generation likelihood, assuming that pre-seen texts will yield higher probabilities [43, 54, 58]. Second,Uncertainty Estimation (UE)focuses on quantifying the confidence in model prediction [33, 48]. UE methods range from latent information- based metrics (e.g., entropy) [10, 12] to consistency-based measures [11, 33]; for instance, [ 33] computes the eigenvalues of a Lapla- cian graph constructed from the semantic similarity of sampled responses. Third,Adaptive Retrievalapproaches [ 19, 21, 44, 51] dy- namically decide when to retrieve external documents. Approaches include monitoring generation probabilities [ 21, 44], leveraging internal model states [51], or employing external classifiers [19] to"},{"citing_arxiv_id":"2511.20284","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Can LLMs Make (Personalized) Access Control Decisions?","primary_cat":"cs.CR","submitted_at":"2025-11-25T13:11:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLMs reflect users' privacy preferences in access control decisions with up to 86% agreement and can promote safer behavior, but personalization trades off higher individual match for potentially less secure results when users over-permission.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.18562","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models","primary_cat":"cs.CL","submitted_at":"2025-03-24T11:16:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LLMs show improved accuracy on gastroenterology questions but remain overconfident in self-reported certainty across commercial, open-source, and quantized variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.14427","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:25:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.10692","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","primary_cat":"cs.CL","submitted_at":"2024-08-20T09:42:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A regression model using attention features and recurrent uncertainty scores improves selective generation in LLMs over unsupervised and supervised baselines on ten datasets and three models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}