Chinese Large Language Models (LLMs) have recently demonstrated impressive capabilities across various NLP benchmarks and real-world applications. However, the existing benchmarks for comprehensively evaluating these LLMs are still insufficient, particularly in terms of measuring knowledge that LLMs capture. Current datasets collect questions from Chinese examinations across different subjects and educational levels to address this issue. Yet, these benchmarks primarily focus on objective questions such as multiple-choice questions, leading to a lack of diversity in question types. To tackle this problem, we propose LHMKE, a Large-scale, Holistic, and Multi-subject Knowledge Evaluation benchmark in this paper. LHMKE is designed to provide a comprehensive evaluation of the knowledge acquisition capabilities of Chinese LLMs. It encompasses 10,465 questions across 75 tasks covering 30 subjects, ranging from primary school to professional certification exams. Notably, LHMKE includes both objective and subjective questions, offering a more holistic evaluation of the knowledge level of LLMs. We have assessed 11 Chinese LLMs under the zero-shot setting, which aligns with real examinations, and compared their performance across different subjects. We also conduct an in-depth analysis to check whether GPT-4 can automatically score subjective predictions. Our findings suggest that LHMKE is a challenging and advanced testbed for Chinese LLMs.
The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs, many of these focus primarily on capabilities, usually overlooking potential alignment and safety issues. To address this gap, we introduce OpenEval, an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. For capability assessment, we include 12 benchmark datasets to evaluate Chinese LLMs from 4 sub-dimensions: NLP tasks, disciplinary knowledge, commonsense reasoning and mathematical reasoning. For alignment assessment, OpenEval contains 7 datasets that examines the bias, offensiveness and illegalness in the outputs yielded by Chinese LLMs. To evaluate safety, especially anticipated risks (e.g., power-seeking, self-awareness) of advanced LLMs, we include 6 datasets. In addition to these benchmarks, we have implemented a phased public evaluation and benchmark update strategy to ensure that OpenEval is in line with the development of Chinese LLMs or even able to provide cutting-edge benchmark datasets to guide the development of Chinese LLMs. In our first public evaluation, we have tested a range of Chinese LLMs, spanning from 7B to 72B parameters, including both open-source and proprietary models. Evaluation results indicate that while Chinese LLMs have shown impressive performance in certain tasks, more attention should be directed towards broader aspects such as commonsense reasoning, alignment, and safety.
To thoroughly assess the mathematical reasoning abilities of Large Language Models (LLMs), we need to carefully curate evaluation datasets covering diverse mathematical concepts and mathematical problems at different difficulty levels. In pursuit of this objective, we propose FineMath in this paper, a fine-grained mathematical evaluation benchmark dataset for assessing Chinese LLMs. FineMath is created to cover the major key mathematical concepts taught in elementary school math, which are further divided into 17 categories of math word problems, enabling in-depth analysis of mathematical reasoning abilities of LLMs. All the 17 categories of math word problems are manually annotated with their difficulty levels according to the number of reasoning steps required to solve these problems. We conduct extensive experiments on a wide range of LLMs on FineMath and find that there is still considerable room for improvements in terms of mathematical reasoning capability of Chinese LLMs. We also carry out an in-depth analysis on the evaluation process and methods that have been overlooked previously. These two factors significantly influence the model results and our understanding of their mathematical reasoning capabilities. The dataset will be publicly available soon.
Prior research in representation engineering has revealed that LLMs encode concepts within their representation spaces, predominantly centered around English. In this study, we extend this philosophy to a multilingual scenario, delving into multilingual human value concepts in LLMs. Through our comprehensive exploration covering 7 types of human values, 16 languages and 3 LLM series with distinct multilinguality, we empirically substantiate the existence of multilingual human values in LLMs. Further cross-lingual analysis on these concepts discloses 3 traits arising from language resource disparities: cross-lingual inconsistency, distorted linguistic relationships, and unidirectional cross-lingual transfer between high- and low-resource languages, all in terms of human value concepts. Additionally, we validate the feasibility of cross-lingual control over value alignment capabilities of LLMs, leveraging the dominant language as a source language. Drawing from our findings on multilingual value alignment, we prudently provide suggestions on the composition of multilingual data for LLMs pre-training: including a limited number of dominant languages for cross-lingual alignment transfer while avoiding their excessive prevalence, and keeping a balanced distribution of non-dominant languages. We aspire that our findings would contribute to enhancing the safety and utility of multilingual AI.
Large language models (LLMs) have demonstrated remarkable capabilities in text comprehension and logical reasoning, achiving or even surpassing human-level performance in numerous cognition tasks. As LLMs are trained from massive textual outputs of human language cognition, it is natural to ask whether LLMs mirror cognitive language processing. Or to what extend LLMs resemble cognitive language processing? In this paper, we propose a novel method that bridge between LLM representations and human cognition signals to evaluate how effectively LLMs simulate cognitive language processing. We employ Representational Similarity Analysis (RSA) to mearsure the alignment between 16 mainstream LLMs and fMRI signals of the brain. We empirically investigate the impact of a variety of factors (e.g., model scaling, alignment training, instruction appending) on such LLM-brain alignment. Experimental results indicate that model scaling is positively correlated with LLM-brain similarity, and alignment training can significantly improve LLM-brain similarity. Additionally, the performance of a wide range of LLM evaluations (e.g., MMLU, Chatbot Arena) is highly correlated with the LLM-brain similarity.
Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques, which reduce the bits needed for model weights or activations with minimal performance loss, have become popular due to the rise of LLMs. However, most quantization studies use pre-trained LLMs, and the impact of quantization on instruction-tuned LLMs and the relationship between perplexity and benchmark performance of quantized LLMs are not well understood. Evaluation of quantized LLMs is often limited to language modeling and a few classification tasks, leaving their performance on other benchmarks unclear. To address these gaps, we propose a structured evaluation framework consisting of three critical dimensions: (1) knowledge \& capacity, (2) alignment, and (3) efficiency, and conduct extensive experiments across ten diverse benchmarks. Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks. Furthermore, quantized LLMs with larger parameter scales can outperform smaller LLMs. Despite the memory savings achieved through quantization, it can also slow down the inference speed of LLMs. Consequently, substantial engineering efforts and hardware support are imperative to achieve a balanced optimization of decoding speed and memory consumption in the context of quantized LLMs.
The rapid evolution of large language models (LLMs) necessitates effective benchmarks for evaluating their role knowledge, which is essential for establishing connections with the real world and providing more immersive interactions. This paper introduces RoleEval, a bilingual benchmark designed to assess the memorization, utilization, and reasoning capabilities of role knowledge. RoleEval comprises RoleEval-Global (including internationally recognized characters) and RoleEval-Chinese (including characters popular in China), with 6,000 Chinese-English parallel multiple-choice questions focusing on 300 influential people and fictional characters drawn from a variety of domains including celebrities, anime, comics, movies, TV series, games, and fiction. These questions cover basic knowledge and multi-hop reasoning abilities, aiming to systematically probe various aspects such as personal information, relationships, abilities, and experiences of the characters. To maintain high standards, we perform a hybrid quality check process combining automatic and human verification, ensuring that the questions are diverse, challenging, and discriminative. Our extensive evaluations of RoleEval across various open-source and proprietary large language models, under both the zero- and few-shot settings, reveal insightful findings. Notably, while GPT-4 outperforms other models on RoleEval-Global, Chinese LLMs excel on RoleEval-Chinese, highlighting significant knowledge distribution differences. We expect that RoleEval will highlight the significance of assessing role knowledge for foundation models across various languages and cultural settings.
As an indispensable ingredient of intelligence, commonsense reasoning is crucial for large language models (LLMs) in real-world scenarios. In this paper, we propose CORECODE, a dataset that contains abundant commonsense knowledge manually annotated on dyadic dialogues, to evaluate the commonsense reasoning and commonsense conflict detection capabilities of Chinese LLMs. We categorize commonsense knowledge in everyday conversations into three dimensions: entity, event, and social interaction. For easy and consistent annotation, we standardize the form of commonsense knowledge annotation in open-domain dialogues as "domain: slot = value". A total of 9 domains and 37 slots are defined to capture diverse commonsense knowledge. With these pre-defined domains and slots, we collect 76,787 commonsense knowledge annotations from 19,700 dialogues through crowdsourcing. To evaluate and enhance the commonsense reasoning capability for LLMs on the curated dataset, we establish a series of dialogue-level reasoning and detection tasks, including commonsense knowledge filling, commonsense knowledge generation, commonsense conflict phrase detection, domain identification, slot identification, and event causal inference. A wide variety of existing open-source Chinese LLMs are evaluated with these tasks on our dataset. Experimental results demonstrate that these models are not competent to predict CORECODE's plentiful reasoning content, and even ChatGPT could only achieve 0.275 and 0.084 accuracy on the domain identification and slot identification tasks under the zero-shot setting. We release the data and codes of CORECODE at https://github.com/danshi777/CORECODE to promote commonsense reasoning evaluation and study of LLMs in the context of daily conversations.
Recently, artificial intelligence has been extensively deployed across various scientific disciplines, optimizing and guiding the progression of experiments through the integration of abundant datasets, whilst continuously probing the vast theoretical space encapsulated within the data. Particularly, deep learning models, due to their end-to-end adaptive learning capabilities, are capable of autonomously learning intrinsic data features, thereby transcending the limitations of traditional experience to a certain extent. Here, we unveil previously unreported information characteristics pertaining to different frequencies emerged during our work on predicting the terahertz spectral modulation effects of metasurfaces based on AI-prediction. Moreover, we have substantiated that our proposed methodology of simply adding supplementary multi-frequency inputs to the existing dataset during the target spectral prediction process can significantly enhance the predictive accuracy of the network. This approach effectively optimizes the utilization of existing datasets and paves the way for interdisciplinary research and applications in artificial intelligence, chemistry, composite material design, biomedicine, and other fields.
The effective assessment of the instruction-following ability of large language models (LLMs) is of paramount importance. A model that cannot adhere to human instructions might be not able to provide reliable and helpful responses. In pursuit of this goal, various benchmarks have been constructed to evaluate the instruction-following capacity of these models. However, these benchmarks are limited to a single language and are constructed using automated approaches, which restricts their applicability and the quality of the test examples they contain. To bridge this gap, we introduce the FollowEval benchmark in this paper. This benchmark is composed of instances in both English and Chinese, and all test examples are crafted by human experts. Furthermore, the FollowEval benchmark is designed to assess LLMs across five critical dimensions of instruction following: string manipulation, commonsense reasoning, logical reasoning, spatial reasoning, and response constraints. To enhance the complexity and present a sufficient challenge, each test example is designed to evaluate more than one dimension. We have evaluated various LLMs using the FollowEval benchmark and found that their performance significantly lags behind that of humans. This highlights the considerable room for improvement in the instruction-following ability of these models.