SWAN uses AMR to embed semantic watermarks that persist through paraphrases, matching SOTA detection on original text and improving AUC by 13.9 points on paraphrased RealNews data.
CoRR , volume =
6 Pith papers cite this work, alongside 981 external citations. Polarity classification is still indexing.
6
Pith papers citing it
981
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.
Certain dimensions in SONAR sentence embeddings act as anomaly detectors by measuring consistency between successive encoding and decoding.
ConSUM reranks candidate summaries using MBR consensus and source-consistency metrics to improve factuality over standard generation or reranking baselines.
A post-training quantization technique for 1-bit LLMs that corrects layer-wise error accumulation and anisotropic representation distortion to preserve output behavior more effectively than existing methods.
citing papers explorer
-
SWAN: Semantic Watermarking with Abstract Meaning Representation
SWAN uses AMR to embed semantic watermarks that persist through paraphrases, matching SOTA detection on original text and improving AUC by 13.9 points on paraphrased RealNews data.
-
Learning to summarize from human feedback
Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.
-
Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector
Certain dimensions in SONAR sentence embeddings act as anomaly detectors by measuring consistency between successive encoding and decoding.
-
Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding
ConSUM reranks candidate summaries using MBR consensus and source-consistency metrics to improve factuality over standard generation or reranking baselines.
-
Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models
A post-training quantization technique for 1-bit LLMs that corrects layer-wise error accumulation and anisotropic representation distortion to preserve output behavior more effectively than existing methods.
- From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction