Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG

• URL: http://arxiv.org/abs/2406.13069v3
• Date: Fri, 04 Oct 2024 16:42:20 GMT
• Title: Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG
• Authors: William Merrill, Noah A. Smith, Yanai Elazar,
• Abstract summary: We investigate the extent to which modern LMs generate $n$-grams from their training data. We develop Rusty-DAWG, a novel search tool inspired by indexing of genomic data.
• Score: 57.14250086701313
• License:
• Abstract: How novel are texts generated by language models (LMs) relative to their training corpora? In this work, we investigate the extent to which modern LMs generate $n$-grams from their training data, evaluating both (i) the probability LMs assign to complete training $n$-grams and (ii) $n$-novelty, the proportion of $n$-grams generated by an LM that did not appear in the training data (for arbitrarily large $n$). To enable arbitrary-length $n$-gram search over a corpus in constant time w.r.t. corpus size, we develop Rusty-DAWG, a novel search tool inspired by indexing of genomic data. We compare the novelty of LM-generated text to human-written text and explore factors that affect generation novelty, focusing on the Pythia models. We find that, for $n > 4$, LM-generated text is less novel than human-written text, though it is more novel for smaller $n$. Larger LMs and more constrained decoding strategies both decrease novelty. Finally, we show that LMs complete $n$-grams with lower loss if they are more frequent in the training data. Overall, our results reveal factors influencing the novelty of LM-generated text, and we release Rusty-DAWG to facilitate further pretraining data research.

Related papers

• Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens [138.36729703589512]
  We show that $n$-gram language models are still relevant in this era of neural large language models (LLMs) This was done by modernizing $n$-gram LMs in two aspects. First, we train them at the same data scale as neural LLMs -- 5 trillion tokens. Second, existing $n$-gram LMs use small $n$ which hinders their performance; we instead allow $n$ to be arbitrarily large, by introducing a new $infty$-gram LM with backoff.
  arXiv  Detail & Related papers  (2024-01-30T19:03:49Z)
• TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles [14.205559299967423]
  Recent advances in Large Language Models (LLMs) have enabled the generation of open-ended high-quality texts, that are non-trivial to distinguish from human-written texts. Users with malicious intent can easily use these open-sourced LLMs to generate harmful texts and dis/misinformation at scale. To mitigate this problem, a computational method to determine if a given text is a deepfake text or not is desired. We propose TopFormer to improve existing AA solutions by capturing more linguistic patterns in deepfake texts.
  arXiv  Detail & Related papers  (2023-09-22T15:32:49Z)
• Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval [51.437420003471615]
  We propose the Retrieval-Pretrained Transformer (RPT), an architecture and training procedure for jointly training a retrieval-augmented LM from scratch. RPT improves retrieval quality and subsequently perplexity across the board compared to strong baselines.
  arXiv  Detail & Related papers  (2023-06-23T10:18:02Z)
• Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study [115.96080028033904]
  We study a scalable pre-trained retrieval-augmented LM (i.e., RETRO) compared with standard GPT and retrieval-augmented GPT. Our findings highlight the promising direction of pretraining autoregressive LMs with retrieval as future foundation models.
  arXiv  Detail & Related papers  (2023-04-13T18:04:19Z)
• Stealing the Decoding Algorithms of Language Models [56.369946232765656]
  A key component of generating text from modern language models (LM) is the selection and tuning of decoding algorithms. In this work, we show, for the first time, that an adversary with typical API access to an LM can steal the type and hyper parameters of its decoding algorithms. Our attack is effective against popular LMs used in text generation APIs, including GPT-2, GPT-3 and GPT-Neo.
  arXiv  Detail & Related papers  (2023-03-08T17:15:58Z)
• Discovering Language Model Behaviors with Model-Written Evaluations [18.24267922379281]
  As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Here, we automatically generate evaluations with LMs. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size.
  arXiv  Detail & Related papers  (2022-12-19T05:13:52Z)
• You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM [65.74934004876914]
  Retrieval-enhanced language models (LMs) condition their predictions on text retrieved from large external datastores. One such approach, the $k$NN-LM, interpolates any existing LM's predictions with the output of a $k$-nearest neighbors model. We empirically measure the effectiveness of our approach on two English language modeling datasets.
  arXiv  Detail & Related papers  (2022-10-28T02:57:40Z)
• Residual Learning of Neural Text Generation with $n$-gram Language Model [41.26228768053928]
  We learn a neural LM that fits the residual between an $n$-gram LM and the real-data distribution. Our approach attains additional performance gains over popular standalone neural models consistently.
  arXiv  Detail & Related papers  (2022-10-26T02:42:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.