Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 3,000 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

We introduce NATURAL PLAN, a realistic planning benchmark in natural language containing 3 key tasks: Trip Planning, Meeting Planning, and Calendar Scheduling. We focus our evaluation on the planning capabilities of LLMs with full information on the task, by providing outputs from tools such as Google Flights, Google Maps, and Google Calendar as contexts to the models. This eliminates the need for a tool-use environment for evaluating LLMs on Planning. We observe that NATURAL PLAN is a challenging benchmark for state of the art models. For example, in Trip Planning, GPT-4 and Gemini 1.5 Pro could only achieve 31.1% and 34.8% solve rate respectively. We find that model performance drops drastically as the complexity of the problem increases: all models perform below 5% when there are 10 cities, highlighting a significant gap in planning in natural language for SoTA LLMs. We also conduct extensive ablation studies on NATURAL PLAN to further shed light on the (in)effectiveness of approaches such as self-correction, few-shot generalization, and in-context planning with long-contexts on improving LLM planning.

We present an approach called Q-probing to adapt a pre-trained language model to maximize a task-specific reward function. At a high level, Q-probing sits between heavier approaches such as finetuning and lighter approaches such as few shot prompting, but can also be combined with either. The idea is to learn a simple linear function on a model's embedding space that can be used to reweight candidate completions. We theoretically show that this sampling procedure is equivalent to a KL-constrained maximization of the Q-probe as the number of samples increases. To train the Q-probes we consider either reward modeling or a class of novel direct policy learning objectives based on importance weighted policy gradients. With this technique, we see gains in domains with ground-truth rewards (code generation) as well as implicit rewards defined by preference data, even outperforming finetuning in data-limited regimes. Moreover, a Q-probe can be trained on top of an API since it only assumes access to sampling and embeddings. Code: https://github.com/likenneth/q_probe .

Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning. However, there is growing concern that some of this performance actually reflects dataset contamination, where data closely resembling benchmark questions leaks into the training data, instead of true reasoning ability. To investigate this claim rigorously, we commission Grade School Math 1000 (GSM1k). GSM1k is designed to mirror the style and complexity of the established GSM8k benchmark, the gold standard for measuring elementary mathematical reasoning. We ensure that the two benchmarks are comparable across important metrics such as human solve rates, number of steps in solution, answer magnitude, and more. When evaluating leading open- and closed-source LLMs on GSM1k, we observe accuracy drops of up to 13%, with several families of models (e.g., Phi and Mistral) showing evidence of systematic overfitting across almost all model sizes. At the same time, many models, especially those on the frontier, (e.g., Gemini/GPT/Claude) show minimal signs of overfitting. Further analysis suggests a positive relationship (Spearman's r^2=0.32) between a model's probability of generating an example from GSM8k and its performance gap between GSM8k and GSM1k, suggesting that many models may have partially memorized GSM8k.

Large language models have astounded the world with fascinating new capabilities. However, they currently lack the ability to teach themselves new skills, relying instead on large amounts of human-generated training data. We introduce SECToR (Self-Education via Chain-of-Thought Reasoning), a proof-of-concept demonstration that language models can teach themselves new skills using chain-of-thought reasoning. During the self-learning loop, SECToR asks models to solve addition problems using chain-of-thought reasoning before training the next version of the model to solve those same problems directly without using such reasoning. This process often results in an improved model which can, when again augmented with chain-of-thought reasoning, solve even harder problems than the original model, allowing the self-learning loop to continue. Language models trained via SECToR autonomously learn to add up to the longest-length-digit numbers without access to any ground truth examples beyond an initial supervised fine-tuning phase consisting only of numbers with 6 or fewer digits. Our central hypothesis is that chain-of-thought reasoning can act as a policy improvement operator, similarly to how Monte-Carlo Tree Search is used in AlphaZero (Silver et al., 2017). We hope that this research can lead to new directions in which language models can learn to teach themselves without the need for human demonstrations.

How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models that simply plagiarize from the training set. On the other hand, statistical evaluation (i.e., perplexity) captures diversity but not quality, as models that occasionally emit low quality samples would be insufficiently penalized. In this paper, we propose a unified framework which evaluates both diversity and quality, based on the optimal error rate of predicting whether a sentence is human- or machine-generated. We demonstrate that this error rate can be efficiently estimated by combining human and statistical evaluation, using an evaluation metric which we call HUSE. On summarization and chit-chat dialogue, we show that (i) HUSE detects diversity defects which fool pure human evaluation and that (ii) techniques such as annealing for improving quality actually decrease HUSE due to decreased diversity.