What Kinds of Tokens Benefit from Distant Text? An Analysis on Long Context Language Modeling

• URL: http://arxiv.org/abs/2406.11238v1
• Date: Mon, 17 Jun 2024 06:07:29 GMT
• Title: What Kinds of Tokens Benefit from Distant Text? An Analysis on Long Context Language Modeling
• Authors: Yutong Hu, Quzhe Huang, Kangcheng Luo, Yansong Feng,
• Abstract summary: We study which kinds of words benefit more from long contexts in language models. We find that content words (e.g., nouns, adjectives) and the initial tokens of words benefit the most. We also observe that language models become more confident with longer contexts, resulting in sharper probability distributions.
• Score: 27.75379365518913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As the context length that large language models can handle continues to increase, these models demonstrate an enhanced ability to utilize distant information for tasks such as language modeling. This capability contrasts with human reading and writing habits, where it is uncommon to remember and use particularly distant information, except in cases of foreshadowing. In this paper, we aim to explore which kinds of words benefit more from long contexts in language models. By analyzing the changes in token probabilities with increasing context length, we find that content words (e.g., nouns, adjectives) and the initial tokens of words benefit the most. Frequent patterns in the context (N-grams) also significantly impact predictions. Additionally, the model's prior knowledge plays a crucial role in influencing predictions, especially for rare tokens. We also observe that language models become more confident with longer contexts, resulting in sharper probability distributions. This overconfidence may contribute to the increasing probabilities of tokens with distant contextual information. We hope that our analysis will help the community better understand long-text language modeling and contribute to the design of more reliable long-context models.

Related papers

• Lost in the Middle: How Language Models Use Long Contexts [88.78803442320246]
  We analyze the performance of language models on two tasks that require identifying relevant information in their input contexts. We find that performance can degrade significantly when changing the position of relevant information. Our analysis provides a better understanding of how language models use their input context and provides new evaluation protocols for future long-context language models.
  arXiv  Detail & Related papers  (2023-07-06T17:54:11Z)
• Language Model Behavior: A Comprehensive Survey [5.663056267168211]
  We discuss over 250 recent studies of English language model behavior before task-specific fine-tuning. Despite dramatic increases in generated text quality as models scale to hundreds of billions of parameters, the models are still prone to unfactual responses, commonsense errors, memorized text, and social biases.
  arXiv  Detail & Related papers  (2023-03-20T23:54:26Z)
• Black-box language model explanation by context length probing [7.526153863886609]
  We present context length probing, a novel explanation technique for causal language models. The technique is model-agnostic and does not rely on access to model internals beyond computing token-level probabilities. We apply context length probing to large pre-trained language models and offer some initial analyses and insights.
  arXiv  Detail & Related papers  (2022-12-30T16:24:10Z)
• What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary [68.77983831618685]
  We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval.
  arXiv  Detail & Related papers  (2022-12-20T16:03:25Z)
• Lexical Generalization Improves with Larger Models and Longer Training [42.024050065980845]
  We analyze the use of lexical overlaps in natural language inference, paraphrase detection, and reading comprehension. We find that larger models are much less susceptible to adopting lexical overlaps.
  arXiv  Detail & Related papers  (2022-10-23T09:20:11Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models [29.993190226231793]
  We use chain-of-thought prompts to introduce structures from probabilistic models into large language models. Our prompts lead language models to infer latent variables and reason about their relationships in order to choose appropriate paraphrases for metaphors.
  arXiv  Detail & Related papers  (2022-09-16T19:23:13Z)
• Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models [62.41139712595334]
  We propose a novel pre-training paradigm for Chinese -- Lattice-BERT. We construct a lattice graph from the characters and words in a sentence and feed all these text units into transformers. We show that our model can bring an average increase of 1.5% under the 12-layer setting.
  arXiv  Detail & Related papers  (2021-04-15T02:36:49Z)
• Understanding and Enhancing the Use of Context for Machine Translation [2.367786892039871]
  This thesis focuses on understanding certain potentials of contexts in neural models and design augmentation models to benefit from them. To translate from a source language to a target language, a neural model has to understand the meaning of constituents in the provided context. Looking more in-depth into the role of context and the impact of data on learning models is essential to advance the NLP field.
  arXiv  Detail & Related papers  (2021-02-20T20:19:27Z)
• Multi-timescale Representation Learning in LSTM Language Models [69.98840820213937]
  Language models must capture statistical dependencies between words at timescales ranging from very short to very long. We derived a theory for how the memory gating mechanism in long short-term memory language models can capture power law decay. Experiments showed that LSTM language models trained on natural English text learn to approximate this theoretical distribution.
  arXiv  Detail & Related papers  (2020-09-27T02:13:38Z)
• Probing Contextual Language Models for Common Ground with Visual Representations [76.05769268286038]
  We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans.
  arXiv  Detail & Related papers  (2020-05-01T21:28:28Z)

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.