Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
hub
On Faithfulness and Factuality in Abstractive Summarization
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Locate-then-edit succeeds at the same early-to-mid MLP locations in masked diffusion models as in autoregressive models, but requires optimization over intermediate partial-mask states to handle multi-token targets.
LLMs routinely produce unsupported causal stories for personal sensing anomalies, and richer evidence or constrained prompts do not reliably eliminate this epistemic overreach.
MÖVE presents a new German-language benchmark evaluating 39 LLMs on performance and governance criteria using ten public-administration datasets.
Diffusion-based localized editing framework for faithful summarization of evolving contexts, introducing the StreamSum benchmark and showing tradeoffs in faithfulness, speed, and preservation.
LMs systematically inflate expressed certainty during rewriting, affecting up to 75% of outputs with a 1.5-2x bias toward increasing rather than decreasing certainty, and the effect compounds over iterations.
Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
PrimeFacts extracts decontextualized premises from fact-check articles, raising evidence retrieval MRR by up to 30% and verdict prediction Macro-F1 by 10-20 points over baselines.
SCURank ranks multiple summary candidates with Summary Content Units to outperform ROUGE and LLM-based methods in summarization distillation.
Short-form factual consistency metrics produce inconsistent scores on semantically equivalent long-document summaries and lose reliability on information-dense claims.
SelfCheckGPT detects hallucinations by checking consistency across multiple sampled responses from black-box LLMs on WikiBio biography generation tasks.
ConSUM reranks candidate summaries using MBR consensus and source-consistency metrics to improve factuality over standard generation or reranking baselines.
ECPO is a listwise policy optimization method that couples ranking utility with span-level evidence certificate validity and a deterministic verifier reward on MAVEN-ERE and RAMS datasets.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.
Mistral uses careful lexical simplification to raise readability while keeping BERTScore at 0.91 comparable to humans, whereas QWen improves readability but shows a disconnect with its 0.89 BERTScore in biomedical text simplification.
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
A survey classifying hallucination phenomena specific to large foundation models, establishing evaluation criteria, examining mitigation strategies, and discussing future directions.
Fine-tuned PEGASUS achieves state-of-the-art ROUGE scores on XL-Sum English corpus with 4.04% ROUGE-1, 15.25% ROUGE-2, and 3.39% ROUGE-L gains over mT5 baseline.
citing papers explorer
-
Stress Testing Factual Consistency Metrics for Long-Document Summarization
Short-form factual consistency metrics produce inconsistent scores on semantically equivalent long-document summaries and lose reliability on information-dense claims.
-
Making Knowledge Accessible: Divergent Readability-Accuracy Strategies of Mistral and QWen in Biomedical Text Simplification
Mistral uses careful lexical simplification to raise readability while keeping BERTScore at 0.91 comparable to humans, whereas QWen improves readability but shows a disconnect with its 0.89 BERTScore in biomedical text simplification.