Automatic grading of subjective questions remains a significant challenge in examination assessment due to the diversity in question formats and the open-ended nature of student responses. Existing works primarily focus on a specific type of subjective question and lack the generality to support comprehensive exams that contain diverse question types. In this paper, we propose a unified Large Language Model (LLM)-enhanced auto-grading framework that provides human-like evaluation for all types of subjective questions across various domains. Our framework integrates four complementary modules to holistically evaluate student answers. In addition to a basic text matching module that provides a foundational assessment of content similarity, we leverage the powerful reasoning and generative capabilities of LLMs to: (1) compare key knowledge points extracted from both student and reference answers, (2) generate a pseudo-question from the student answer to assess its relevance to the original question, and (3) simulate human evaluation by identifying content-related and non-content strengths and weaknesses. Extensive experiments on both general-purpose and domain-specific datasets show that our framework consistently outperforms traditional and LLM-based baselines across multiple grading metrics. Moreover, the proposed system has been successfully deployed in real-world training and certification exams at a major e-commerce enterprise.

Large Reasoning Models (LRMs) with long chain-of-thought capabilities, optimized via reinforcement learning with verifiable rewards (RLVR), excel at objective reasoning tasks like mathematical problem solving and code generation. However, RLVR is known for degrading generation diversity, which causes LRMs to fall short on subjective reasoning that has multiple answers depending on different role perspectives. While recent studies recognize the importance of diversity-enhanced training in objective reasoning, limited attention has been given to subjective tasks. In this paper, we find that subjective reasoning can be improved by introducing perspective diversity and token-level diversity, with the former one providing a coherent scaffolding anchored to a real-world stakeholder group and the latter one broadening the answer search space. We propose MultiRole-R1, a diversity-enhanced training framework featuring an unsupervised data construction pipeline that synthesizes reasoning chains incorporating various role perspectives. It also employs reinforcement learning via Group Relative Policy Optimization with reward shaping, taking diversity as a reward signal in addition to verifiable reward. Training on subjective tasks solely, MultiRole-R1 increases the in-domain and out-of-domain accuracy by 14.1% and 7.64%, and even enhances the performance on advanced math reasoning such as AIME 2024. We further show that diversity is a more consistent indicator of accuracy than reasoning length.

The emergence of Large Language Models (LLMs) in the medical domain has stressed a compelling need for standard datasets to evaluate their question-answering (QA) performance. Although there have been several benchmark datasets for medical QA, they either cover common knowledge across different departments or are specific to another department rather than pediatrics. Moreover, some of them are limited to objective questions and do not measure the generation capacity of LLMs. Therefore, they cannot comprehensively assess the QA ability of LLMs in pediatrics. To fill this gap, we construct PediaBench, the first Chinese pediatric dataset for LLM evaluation. Specifically, it contains 4,565 objective questions and 1,632 subjective questions spanning 12 pediatric disease groups. It adopts an integrated scoring criterion based on different difficulty levels to thoroughly assess the proficiency of an LLM in instruction following, knowledge understanding, clinical case analysis, etc. Finally, we validate the effectiveness of PediaBench with extensive experiments on 20 open-source and commercial LLMs. Through an in-depth analysis of experimental results, we offer insights into the ability of LLMs to answer pediatric questions in the Chinese context, highlighting their limitations for further improvements. Our code and data are published at https://github.com/ACMISLab/PediaBench.

Do large language models (LLMs) have their own worldviews and personality tendencies? Simulations in which an LLM was asked to answer subjective questions were conducted more than 1 million times. Comparison of the responses from different LLMs with real data from the European Social Survey (ESS) suggests that the effect of prompts on bias and variability is fundamental, highlighting major cultural, age, and gender biases. Methods for measuring the difference between LLMs and survey data are discussed, such as calculating weighted means and a new proposed measure inspired by Jaccard similarity. We conclude that it is important to analyze the robustness and variability of prompts before using LLMs to model individual decisions or collective behavior, as their imitation abilities are approximate at best.

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.

Recently, the evaluation of Large Language Models has emerged as a popular area of research. The three crucial questions for LLM evaluation are ``what, where, and how to evaluate''. However, the existing research mainly focuses on the first two questions, which are basically what tasks to give the LLM during testing and what kind of knowledge it should deal with. As for the third question, which is about what standards to use, the types of evaluators, how to score, and how to rank, there hasn't been much discussion. In this paper, we analyze evaluation methods by comparing various criteria with both manual and automatic evaluation, utilizing onsite, crowd-sourcing, public annotators and GPT-4, with different scoring methods and ranking systems. We propose a new dataset, LLMEval and conduct evaluations on 20 LLMs. A total of 2,186 individuals participated, leading to the generation of 243,337 manual annotations and 57,511 automatic evaluation results. We perform comparisons and analyses of different settings and conduct 10 conclusions that can provide some insights for evaluating LLM in the future. The dataset and the results are publicly available at https://github.com/llmeval .

Do you ever find yourself captivated by a song but struggling to put into words what makes it so special? Have you ever wanted to identify the instrument or genre of a piece of music but found yourself at a loss? Perhaps you've tried to search for a particular song through text, only to hit a dead end in your quest. In the world of music information retrieval, the tasks of transcribing music scores and retrieving music based on its characteristics are critical areas of research and advanced techniques may help you sometimes. However, for everyday music enthusiasts without formal training, achieving these goals in pre-defined scientific terms can often feel elusive.

Their joint effects give rise to the variation in responses to the same question by different crowdworkers. This variation is low when the question is easy to answer and objective, and high when it is difficult and subjective. Unfortunately, current quality control methods for crowdsourcing consider only the question difficulty to account for the variation. As a result, these methods cannot distinguish workers' personal preferences for different correct answers of a partially subjective question from their ability/expertise to avoid objectively wrong answers for that question. To address this issue, we present a probabilistic model which (i) explicitly encodes question difficulty as a model parameter and (ii) implicitly encodes question subjectivity via latent preference factors for crowd-workers. We show that question subjectivity induces grouping of crowd-workers, revealed through clustering of their latent preferences. Moreover, we develop a quantitative measure of the subjectivity of a question. Experiments show that our model (1) improves the performance of both quality control for crowdsourced answers and next answer prediction for crowd-workers, and (2) can potentially provide coherent rankings of questions in terms of their difficulty and subjectivity, so that task providers can refine their designs of the crowdsourcing tasks, e.g. by removing highly subjective questions or inappropriately difficult questions.

Automatic Subjective Question Answering (ASQA), which aims at answering users'subjective questions using summaries of multiple opinions, becomes increasingly important. One challenge of ASQA is that expected answers for subjective questions may not readily exist in the Web. The rising and popularity of Community Question Answering (CQA) sites, which provide platforms for people to post and answer questions, provides an alternative to ASQA. One important task of ASQA is question subjectivity identification, which identifies whether a user is asking a subjective question. Unfortunately, there has been little labeled training data available for this task. In this paper, we propose an approach to collect training data automatically by utilizing social signals in CQA sites without involving any manual labeling. Experimental results show that our data-driven approach achieves 9.37% relative improvement over the supervised approach using manually labeled data, and achieves 5.15% relative gain over a state-of-the-art semi-supervised approach. In addition, we propose several heuristic features for question subjectivity identification. By adding these features, we achieve 11.23% relative improvement over word n-gram feature under the same experimental setting.