An official website of the United States government
While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM reasoning is challenging because system capabilities continue to grow while benchmark datasets for tasks like logical deduction have remained static. We introduce MuSR, a dataset for evaluating language models on multistep soft reasoning tasks specified in a natural language narrative. This dataset has two crucial features. First, it is created through a novel neurosymbolic synthetic-to-natural generation algorithm, enabling the construction of complex reasoning instances that challenge GPT-4 (e.g., murder mysteries roughly 1000 words in length) and which can be scaled further as more capable LLMs are released. Second, our dataset instances are free text narratives corresponding to real-world domains of reasoning; this makes it simultaneously much more challenging than other synthetically-crafted benchmarks while remaining realistic and tractable for human annotators to solve with high accuracy. We evaluate a range of LLMs and prompting techniques on this dataset and characterize the gaps that remain for techniques like chain-of-thought to perform robust reasoning.
more »
« less
This content will become publicly available on June 1, 2026
Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks
This paper presents AutoEval, a novel benchmark for scaling Large Language Model (LLM) assessment in formal tasks with clear notions of correctness, such as truth maintenance in translation and logical reasoning. AutoEval is the first benchmarking paradigm that offers several key advantages necessary for scaling objective evaluation of LLMs without human labeling: (a) ability to evaluate LLMs of increasing sophistication by auto-generating tasks at different levels of difficulty; (b) auto-generation of ground truth that eliminates dependence on expensive and time-consuming human annotation; (c) the use of automatically generated, randomized datasets that mitigate the ability of successive LLMs to overfit to static datasets used in many contemporary benchmarks. Empirical analysis shows that an LLM's performance on AutoEval is highly indicative of its performance on a diverse array of other benchmarks focusing on translation and reasoning tasks, making it a valuable autonomous evaluation paradigm in settings where hand-curated datasets can be hard to obtain and/or update.
more »
« less
- Award ID(s):
- 1942856
- PAR ID:
- 10616196
- Publisher / Repository:
- The Thirteenth International Conference on Learning Representations
- Date Published:
- ISBN:
- 9798331320850
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
High-quality benchmarks are essential for evaluating reasoning and retrieval capabilities of large language models (LLMs). However, curating datasets for this purpose is not a permanent solution as they are prone to data leakage and inflated performance results. To address these challenges, we propose PhantomWiki: a pipeline to generate unique and factually consistent document corpora with diverse question-answer pairs. Unlike prior work, PhantomWiki is neither a fixed dataset, nor is it based on any existing data. Instead, a new PhantomWiki instance is generated on demand for each evaluation. We vary the question difficulty and corpus size to disentangle reasoning and retrieval capabilities respectively, and find that PhantomWiki datasets are surprisingly challenging for frontier LLMs. Thus, we contribute a scalable and data leakage-resistant framework for disentangled evaluation of reasoning, retrieval, and tool-use abilities.more » « less
-
Training emotion recognition models has relied heavily on human annotated data, which present diversity, quality, and cost challenges. In this paper, we explore the potential of Large Language Models (LLMs), specifically GPT-4, in automating or assisting emotion annotation. We compare GPT-4 with supervised models and/or humans in three aspects: agreement with human annotations, alignment with human perception, and impact on model training. We find that common metrics that use aggregated human annotations as ground truth can underestimate GPT-4's performance, and our human evaluation experiment reveals a consistent preference for GPT-4 annotations over humans across multiple datasets and evaluators. Further, we investigate the impact of using GPT-4 as an annotation filtering process to improve model training. Together, our findings highlight the great potential of LLMs in emotion annotation tasks and underscore the need for refined evaluation methodologies.more » « less
-
Machine learning (ML) pervades the field of Automated Program Repair (APR). Algorithms deploy neural machine translation and large language models (LLMs) to generate software patches, among other tasks. But, there are important differences between these applications of ML and earlier work, which complicates the task of ensuring that results are valid and likely to generalize. A challenge is that the most popular APR evaluation benchmarks were not designed with ML techniques in mind. This is especially true for LLMs, whose large and often poorly-disclosed training datasets may include problems on which they are evaluated. This article reviews work in APR published in the field’s top five venues since 2018, emphasizing emerging trends in the field, including the dramatic rise of ML models, including LLMs. ML-based articles are categorized along structural and functional dimensions, and a variety of issues are identified that these new methods raise. Importantly, data leakage and contamination concerns arise from the challenge of validating ML-based APR using existing benchmarks, which were designed before these techniques were popular. We discuss inconsistencies in evaluation design and performance reporting and offer pointers to solutions where they are available. Finally, we highlight promising new directions that the field is already taking.more » « less
-
Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws. While LLM-based data quality rating systems offer a cost-effective alternative to human annotation, they often suffer from inaccuracies and biases, even in powerful models like GPT-4. In this work, we introduce DS2, a Diversity-aware Score curation method for Data Selection. By systematically modeling error patterns through a score transition matrix, DS2 corrects LLM-based scores and promotes diversity in the selected data samples. Our approach shows that a curated subset (just 3.3% of the original dataset) outperforms full-scale datasets (300k samples) across various machine-alignment benchmarks, and matches or surpasses human-aligned datasets such as LIMA with the same sample size (1k samples). These findings challenge conventional data scaling assumptions, highlighting that redundant, low-quality samples can degrade performance and reaffirming that "more can be less."more » « less
