A 1.88-million-article biomedical summarization dataset is released and quality-aware selection of training data based on abstract alignment outperforms random sampling on factuality metrics.
A lign S core: Evaluating Factual Consistency with A Unified Alignment Function
9 Pith papers cite this work, alongside 50 external citations. Polarity classification is still indexing.
9
Pith papers citing it
50
external citations · OpenAlex
representative citing papers
RCA is a training-free module that boosts input context signal strength in the residual stream of LLMs by orthogonal decoupling of attention routing from value magnitude.
DPR-BAG generates biomedical abstracts from full texts via BOMRC decomposition, parallel LLM summarization, and refinement, showing higher abstractive novelty than baselines while preserving factual consistency on a 46k-article PMC dataset.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Short-form factual consistency metrics produce inconsistent scores on semantically equivalent long-document summaries and lose reliability on information-dense claims.
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
A factorized study finds raw hidden states and attention features hard to beat in-domain for LLM uncertainty probes, but structured compressed features are more robust under distribution shift, with pretrained probes transferring to open-ended generation.
Disentangling input ambiguity from uncertainty quantification improves error prediction for LLMs on QA tasks, yielding over 10 PRR point gains across models and datasets.
A local lint pipeline verifies paper citations and internal consistency and proposes a SciLint Score combining citation-chain integrity with philosophy-of-science criteria.
citing papers explorer
-
Less is More: Quality-Aware Training Data Selection for Scientific Summarization
A 1.88-million-article biomedical summarization dataset is released and quality-aware selection of training data based on abstract alignment outperforms random sampling on factuality metrics.
-
Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
RCA is a training-free module that boosts input context signal strength in the residual stream of LLMs by orthogonal decoupling of attention routing from value magnitude.
-
Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation
DPR-BAG generates biomedical abstracts from full texts via BOMRC decomposition, parallel LLM summarization, and refinement, showing higher abstractive novelty than baselines while preserving factual consistency on a 46k-article PMC dataset.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
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.
-
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
-
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
A factorized study finds raw hidden states and attention features hard to beat in-domain for LLM uncertainty probes, but structured compressed features are more robust under distribution shift, with pretrained probes transferring to open-ended generation.
-
The Role of Ambiguity in Error Prediction via Uncertainty Quantification
Disentangling input ambiguity from uncertainty quantification improves error prediction for LLMs on QA tasks, yielding over 10 PRR point gains across models and datasets.
-
sciwrite-lint: Verification Infrastructure for the Age of Science Vibe-Writing
A local lint pipeline verifies paper citations and internal consistency and proposes a SciLint Score combining citation-chain integrity with philosophy-of-science criteria.