The paper introduces DEDUCE, a three‑stage framework that turns large language models into proactive error correctors by detecting input fact errors, devising correction strategies, and delivering reliable answers. It also presents MisFactQA, a dataset of factual errors, and new metrics for robustness evaluation. Experiments on TruthfulQA, FalseQA, and MisFactQA show significant gains in accuracy and error correction across Qwen, LLaMA, and Gemma models.
Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input....
arXiv:2608.22483v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is mis...
ReliableRAG is a new framework for Retrieval-Augmented Generation that tackles misinformation in multi‑hop question answering. It extracts structured triples from retrieved documents, evaluates each triple’s reliability by combining semantic relevance to the query with credibility, and keeps only the top‑K reliable, non‑redundant triples. Using these refined triples, the system builds robust reasoning chains that filter out deceptive misinformation and produce accurate, trustworthy answers.
arXiv:2609.15561v1 Announce Type: new Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?...
Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces proposes DDRG, a framework that uses graph alignment to detect claim-level disagreements in reasoning traces and selectively corrects them with a verifier. DDRG builds source‑grounded claim graphs, sends localized conflicts to an answer‑blind verifier, and applies a focused repair only when the verifier supports the majority answer’s path. Experiments on five benchmarks show that zero‑shot DDRG improves macro‑average accuracy by 8.65–15.83 percentage points over direct answering and outperforms CoT, GoT, GoV, and SC on this metric.
arXiv:2607. 26102v1 Announce Type: cross Abstract: Mathematical chain of thought (CoT) evaluation is commonly reduced to whether the final answer matches a reference.
PROOF is a benchmark that profiles the reliability of object-level facts in instruction-tuned language models by converting a frozen Wikidata snapshot into 18,486 English multiple-choice questions grounded in 11,779 semantic facts across 101 classes, 392 properties, and 14 domains. Each question includes an explicit "I don't know" option, a "No correct option" control, and nine controlled formulations, with 1,849 questions designed as no-correct-option traps. The study evaluates 18 open-weight model deployments on 166,374 prompts, revealing wide variability in factual accuracy, sensitivity to wording changes, and the impact of decoder perturbations.
arXiv:2607. 22554v1 Announce Type: new Abstract: Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in different but equivalent ways.
arXiv:2608.29307v1 Announce Type: cross Abstract: Language models increasingly answer questions by consulting retrieved documents rather than memory alone, a design now common in search assistants an...
arXiv:2608.29286v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) evolve into sophisticated interactive assistants, their reliability depends not only on following instructi...
arXiv:2610.18606v1 Announce Type: new Abstract: Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Sel...
GRACE is a step‑level benchmark for evaluating the faithfulness of chain‑of‑thought reasoning over context. It provides human annotations for each step in CoT traces from 10 models across 4 datasets, labeling faithfulness, error category, and natural‑language explanations. The benchmark introduces a data‑driven taxonomy that splits errors into GRACE‑Inference (deductive) and GRACE‑Grounding (factual) tracks, each with four categories, and demonstrates that incorporating step‑level faithfulness signals can improve downstream accuracy and reasoning reliability.