Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Chang, Yapei"'
The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits, which LLM AP
Externí odkaz:
http://arxiv.org/abs/2406.14517
Autor:
Kim, Yekyung, Chang, Yapei, Karpinska, Marzena, Garimella, Aparna, Manjunatha, Varun, Lo, Kyle, Goyal, Tanya, Iyyer, Mohit
Publikováno v:
1st Conference on Language Modeling (COLM 2024)
While long-context large language models (LLMs) can technically summarize book-length documents (>100K tokens), the length and complexity of the documents have so far prohibited evaluations of input-dependent aspects like faithfulness. In this paper,
Externí odkaz:
http://arxiv.org/abs/2404.01261
Summarizing book-length documents (>100K tokens) that exceed the context window size of large language models (LLMs) requires first breaking the input document into smaller chunks and then prompting an LLM to merge, update, and compress chunk-level s
Externí odkaz:
http://arxiv.org/abs/2310.00785
Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To address these
Externí odkaz:
http://arxiv.org/abs/2205.09726
Humanities scholars commonly provide evidence for claims that they make about a work of literature (e.g., a novel) in the form of quotations from the work. We collect a large-scale dataset (RELiC) of 78K literary quotations and surrounding critical a
Externí odkaz:
http://arxiv.org/abs/2203.10053