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.

研究论文探索了长文本语言模型中哪一种词汇能够更多地受益于长上下文，通过分析文本的概率变化，发现内容词汇和词汇的起始部分受益最大，上下文中的频繁模式也对预测产生显著影响，同时，模型的先验知识对预测尤为重要，尤其是对于罕见的词汇，语言模型在长上下文下变得更加自信，这种过度自信可能导致远程上下文信息中的词汇概率增加，希望该分析有助于更好地理解长文本语言建模并设计更可靠的长上下文模型。

远程文本对哪些标记有益处？长上下文语言建模分析

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

LLM text decoding is key component for perceived LLM quality. We demonstrate
two experiments showing that decoding methods could be improved by manipulation
of token probabilities. First, we test few LLM on SummEval summary scoring
dataset, to measure reading comprehension. We compare scores from greedy
decoding to expected values over the next token distribution. We scale logits
by large temperature to increase the entropy of scores. This allows strong
improvement of performance on SummEval (in terms of correlations to human
judgement). We see improvement from 6-8% to 13-28% for 7B Mistral and from
20%-46% to 37%-56% for Mixtral, beating GPT 4 0314 result on two metrics. Part
of the gain seems related to positional bias. Secondly, we use
probability-based tree sampling algorithm, to examine all most probable
generations for given prompt.

LLM 文本解码是感知 LLM 质量的关键组成部分。我们展示了两个实验，证明通过操纵记号概率可以改进解码方法。首先，我们在 SummEval 摘要评分数据集上测试了几个 LLM，以衡量阅读理解能力。我们将得分与下一个记号分布的预期值进行比较，通过放大温度来缩放 logits 以增加得分的熵。这使得在 SummEval 上性能得到了显著提高（通过与人类判断的相关性来衡量）。对于 7B Mistral，我们从 6-8% 提高到 13-28%，对于 Mixtral，我们从 20%-46% 提高到 37%-56%，超过了 GPT 4 0314 在两个度量指标上的结果。提升的一部分似乎与位置偏置相关。其次，我们使用基于概率的树采样算法来检查给定提示的所有最可能生成的结果。

通过期望值计算改进生成式语言模型的阅读理解能力中未使用信息的词汇概率分布

Unused information in token probability distribution of generative LLM:  improving LLM reading comprehension through calculation of expected values

As the use of Large Language Models (LLMs) becomes more widespread,
understanding their self-evaluation of confidence in generated responses
becomes increasingly important as it is integral to the reliability of the
output of these models. We introduce the concept of Confidence-Probability
Alignment, that connects an LLM's internal confidence, quantified by token
probabilities, to the confidence conveyed in the model's response when
explicitly asked about its certainty. Using various datasets and prompting
techniques that encourage model introspection, we probe the alignment between
models' internal and expressed confidence. These techniques encompass using
structured evaluation scales to rate confidence, including answer options when
prompting, and eliciting the model's confidence level for outputs it does not
recognize as its own. Notably, among the models analyzed, OpenAI's GPT-4 showed
the strongest confidence-probability alignment, with an average Spearman's
$\hat{\rho}$ of 0.42, across a wide range of tasks. Our work contributes to the
ongoing efforts to facilitate risk assessment in the application of LLMs and to
further our understanding of model trustworthiness.

通过使用各种数据集和提示技术，本研究探索了大型语言模型（LLMs）内部信心与其对外表达的一致性，其中 OpenAI 的 GPT-4 表现出最强的信心 - 概率对齐性，并有助于评估 LLMs 的风险和提高对模型可信度的认识。