Are Language Model Logits Calibrated?

Some information is factual (e.g., "Paris is in France"), whereas other information is probabilistic (e.g., "the coin flip will be a [Heads/Tails]."). We believe that good Language Models (LMs) should understand and reflect this nuance. Our work investigates this by testing if LMs' output probabilities are calibrated to their textual contexts. We define model "calibration" as the degree to which the output probabilities of candidate tokens are aligned with the relative likelihood that should be inferred from the given context. For example, if the context concerns two equally likely options (e.g., heads or tails for a fair coin), the output probabilities should reflect this. Likewise, context that concerns non-uniformly likely events (e.g., rolling a six with a die) should also be appropriately captured with proportionate output probabilities. We find that even in simple settings the best LMs (1) are poorly calibrated, and (2) have systematic biases (e.g., preferred colors and sensitivities to word orderings). For example, gpt-4o-mini often picks the first of two options presented in the prompt regardless of the options' implied likelihood, whereas Llama-3.1-8B picks the second. Our other consistent finding is mode-collapse: Instruction-tuned models often over-allocate probability mass on a single option. These systematic biases introduce non-intuitive model behavior, making models harder for users to understand.

An Analysis of Multilingual FActScore

FActScore has gained popularity as a metric to estimate the factuality of long-form texts generated by Large Language Models (LLMs) in English. However, there has not been any work in studying the behavior of FActScore in other languages. This paper studies the limitations of each component in the four-component pipeline of FActScore in the multilingual setting. We introduce a new dataset for FActScore on texts generated by strong multilingual LLMs. Our evaluation shows that LLMs exhibit distinct behaviors in both fact extraction and fact scoring tasks. No LLM produces consistent and reliable FActScore across languages with varying levels of resources. We also find that the knowledge source plays an important role in the quality of the estimated FActScore. Using Wikipedia as the knowledge source may hinder the true FActScore of long-form text due to its limited coverage in medium- and low-resource languages. We also incorporate three mitigations to our knowledge source that ultimately improve FActScore estimation across all languages.

SEC-QA: A Systematic Evaluation Corpus for Financial QA

The financial domain frequently deals with large numbers of long documents that are essential for daily operations. Significant effort is put towards automating financial data analysis. However, a persistent challenge, not limited to the finance domain, is the scarcity of datasets that accurately reflect real-world tasks for model evaluation. Existing datasets are often constrained by size, context, or relevance to practical applications. Moreover, LLMs are currently trained on trillions of tokens of text, limiting access to novel data or documents that models have not encountered during training for unbiased evaluation. We propose SEC-QA, a continuous dataset generation framework with two key features: 1) the semi-automatic generation of Question-Answer (QA) pairs spanning multiple long context financial documents, which better represent real-world financial scenarios; 2) the ability to continually refresh the dataset using the most recent public document collections, not yet ingested by LLMs. Our experiments show that current retrieval augmented generation methods systematically fail to answer these challenging multi-document questions. In response, we introduce a QA system based on program-of-thought that improves the ability to perform complex information retrieval and quantitative reasoning pipelines, thereby increasing QA accuracy.

Tokenization Is More Than Compression

Tokenization is a foundational step in Natural Language Processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has been suggested that the effectiveness of BPE stems from its ability to condense text into a relatively small number of tokens. We test the hypothesis that fewer tokens lead to better downstream performance by introducing PathPiece, a new tokenizer that segments a document's text into the minimum number of tokens for a given vocabulary. Through extensive experimentation we find this hypothesis not to be the case, casting doubt on the understanding of the reasons for effective tokenization. To examine which other factors play a role, we evaluate design decisions across all three phases of tokenization: pre-tokenization, vocabulary construction, and segmentation, offering new insights into the design of effective tokenizers. Specifically, we illustrate the importance of pre-tokenization and the benefits of using BPE to initialize vocabulary construction. We train 64 language models with varying tokenization, ranging in size from 350M to 2.4B parameters, all of which are made publicly available.

DocFinQA: A Long-Context Financial Reasoning Dataset

Research in quantitative reasoning within the financial domain indeed necessitates the use of realistic tasks and data, primarily because of the significant impact of decisions made in business and finance. Financial professionals often interact with documents hundreds of pages long, but most research datasets drastically reduce this context length. To address this, we introduce a long-document financial QA task. We augment 7,621 questions from the existing FinQA dataset with full-document context, extending the average context length for each question from under 700 words in FinQA to 123k words in DocFinQA. We conduct extensive experiments of retrieval-based QA pipelines and long-context language models on the augmented data. Our results show that DocFinQA provides challenges for even the strongest, state-of-the-art systems.

BizBench: A Quantitative Reasoning Benchmark for Business and Finance

As large language models (LLMs) impact a growing number of complex domains, it is becoming increasingly important to have fair, accurate, and rigorous evaluation benchmarks. Evaluating the reasoning skills required for business and financial NLP stands out as a particularly difficult challenge. We introduce BizBench, a new benchmark for evaluating models' ability to reason about realistic financial problems. BizBench comprises 8 quantitative reasoning tasks. Notably, BizBench targets the complex task of question-answering (QA) for structured and unstructured financial data via program synthesis (i.e., code generation). We introduce three diverse financially-themed code-generation tasks from newly collected and augmented QA data. Additionally, we isolate distinct financial reasoning capabilities required to solve these QA tasks: reading comprehension of financial text and tables, which is required to extract correct intermediate values; and understanding domain knowledge (e.g., financial formulas) needed to calculate complex solutions. Collectively, these tasks evaluate a model's financial background knowledge, ability to extract numeric entities from financial documents, and capacity to solve problems with code. We conduct an in-depth evaluation of open-source and commercial LLMs, illustrating that BizBench is a challenging benchmark for quantitative reasoning in the finance and business domain.

Mask Conditional Synthetic Satellite Imagery

In this paper we propose a mask-conditional synthetic image generation model for creating synthetic satellite imagery datasets. Given a dataset of real high-resolution images and accompanying land cover masks, we show that it is possible to train an upstream conditional synthetic imagery generator, use that generator to create synthetic imagery with the land cover masks, then train a downstream model on the synthetic imagery and land cover masks that achieves similar test performance to a model that was trained with the real imagery. Further, we find that incorporating a mixture of real and synthetic imagery acts as a data augmentation method, producing better models than using only real imagery (0.5834 vs. 0.5235 mIoU). Finally, we find that encouraging diversity of outputs in the upstream model is a necessary component for improved downstream task performance. We have released code for reproducing our work on GitHub, see https://github.com/ms-synthetic-satellite-image/synthetic-satellite-imagery .

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from literature which uncertainty-aware models are best suited for a given dataset. Thus, we compare six uncertainty-aware deep learning models on a set of edge-case tasks: robustness to adversarial attacks as well as out-of-distribution and adversarial detection. We find that the geometry of the data sub-manifold is an important factor in determining the success of various models. Our finding suggests an interesting direction in the study of uncertainty-aware deep learning models.