MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models

Large language models (LLMs) are commonly used as evaluators in tasks (e.g., reward modeling, LLM-as-a-judge), where they act as proxies for human preferences or judgments. This leads to the need for meta-evaluation: evaluating the credibility of LLMs as evaluators. However, existing benchmarks primarily focus on English, offering limited insight into LLMs' effectiveness as evaluators in non-English contexts. To address this, we introduce MM-Eval, a multilingual meta-evaluation benchmark that covers 18 languages across six categories. MM-Eval evaluates various dimensions, including language-specific challenges like linguistics and language hallucinations. Evaluation results show that both proprietary and open-source language models have considerable room for improvement. Further analysis reveals a tendency for these models to assign middle-ground scores to low-resource languages. We publicly release our benchmark and code.

LLM-as-a-Judge & Reward Model: What They Can and Cannot Do

LLM-as-a-Judge and reward models are widely used alternatives of multiple-choice questions or human annotators for large language model (LLM) evaluation. Their efficacy shines in evaluating long-form responses, serving a critical role as evaluators of leaderboards and as proxies to align LLMs via reinforcement learning. However, despite their popularity, their effectiveness outside of English remains largely unexplored. In this paper, we conduct a comprehensive analysis on automated evaluators, reporting key findings on their behavior in a non-English environment. First, we discover that English evaluation capabilities significantly influence language-specific capabilities, often more than the language proficiency itself, enabling evaluators trained in English to easily transfer their skills to other languages. Second, we identify critical shortcomings, where LLMs fail to detect and penalize errors, such as factual inaccuracies, cultural misrepresentations, and the presence of unwanted language. Finally, we release Kudge, the first non-English meta-evaluation dataset containing 5,012 human annotations in Korean.

The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models

As language models (LMs) become capable of handling a wide range of tasks, their evaluation is becoming as challenging as their development. Most generation benchmarks currently assess LMs using abstract evaluation criteria like helpfulness and harmlessness, which often lack the flexibility and granularity of human assessment. Additionally, these benchmarks tend to focus disproportionately on specific capabilities such as instruction following, leading to coverage bias. To overcome these limitations, we introduce the BiGGen Bench, a principled generation benchmark designed to thoroughly evaluate nine distinct capabilities of LMs across 77 diverse tasks. A key feature of the BiGGen Bench is its use of instance-specific evaluation criteria, closely mirroring the nuanced discernment of human evaluation. We apply this benchmark to assess 103 frontier LMs using five evaluator LMs. Our code, data, and evaluation results are all publicly available at https://github.com/prometheus-eval/prometheus-eval/tree/main/BiGGen-Bench.

ESG Classification by Implicit Rule Learning via GPT-4

Environmental, social, and governance (ESG) factors are widely adopted as higher investment return indicators. Accordingly, ongoing efforts are being made to automate ESG evaluation with language models to extract signals from massive web text easily. However, recent approaches suffer from a lack of training data, as rating agencies keep their evaluation metrics confidential. This paper investigates whether state-of-the-art language models like GPT-4 can be guided to align with unknown ESG evaluation criteria through strategies such as prompting, chain-of-thought reasoning, and dynamic in-context learning. We demonstrate the efficacy of these approaches by ranking 2nd in the Shared-Task ML-ESG-3 Impact Type track for Korean without updating the model on the provided training data. We also explore how adjusting prompts impacts the ability of language models to address financial tasks leveraging smaller models with openly available weights. We observe longer general pre-training to correlate with enhanced performance in financial downstream tasks. Our findings showcase the potential of language models to navigate complex, subjective evaluation guidelines despite lacking explicit training examples, revealing opportunities for training-free solutions for financial downstream tasks.

KMMLU: Measuring Massive Multitask Language Understanding in Korean

We propose KMMLU, a new Korean benchmark with 35,030 expert-level multiple-choice questions across 45 subjects ranging from humanities to STEM. Unlike previous Korean benchmarks that are translated from existing English benchmarks, KMMLU is collected from original Korean exams, capturing linguistic and cultural aspects of the Korean language. We test 26 publically available and proprietary LLMs, identifying significant room for improvement. The best publicly available model achieves 50.54% on KMMLU, far below the average human performance of 62.6%. This model was primarily trained for English and Chinese, not Korean. Current LLMs tailored to Korean, such as Polyglot-Ko, perform far worse. Surprisingly, even the most capable proprietary LLMs, e.g., GPT-4 and HyperCLOVA X, achieve 59.95% and 53.40%, respectively. This suggests that further work is needed to improve Korean LLMs, and KMMLU offers the right tool to track this progress. We make our dataset publicly available on the Hugging Face Hub and integrate the benchmark into EleutherAI's Language Model Evaluation Harness.

Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?

Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task Inference. For this purpose, we introduce the MTI Bench(Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks. Each task in the MTI Bench involves 2 to 3 sub-tasks. As expected, we first demonstrate that Multi-Task Inference reduces the total inference time by 1.46 times in average since it does not require multiple inference calls. Interestingly, contrary to the expectation that LLMs would perform better when tasks are divided, we find that state-of-the-art LLMs, such as Llama-2-Chat-70B and GPT-4, show up to 7.3% and 12.4% improved performance with Multi-Task Inference compared to Single-Task Inference on the MTI Bench. We release the MTI Bench dataset and our code at this link https://github.com/guijinSON/MTI-Bench.

HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models

Large Language Models (LLMs) pretrained on massive corpora exhibit remarkable capabilities across a wide range of tasks, however, the attention given to non-English languages has been limited in this field of research. To address this gap and assess the proficiency of language models in the Korean language and culture, we present HAE-RAE Bench, covering 6 tasks including vocabulary, history, and general knowledge. Our evaluation of language models on this benchmark highlights the potential advantages of employing Large Language-Specific Models(LLSMs) over a comprehensive, universal model like GPT-3.5. Remarkably, our study reveals that models approximately 13 times smaller than GPT-3.5 can exhibit similar performance levels in terms of language-specific knowledge retrieval. This observation underscores the importance of homogeneous corpora for training professional-level language-specific models. On the contrary, we also observe a perplexing performance dip in these smaller LMs when they are tasked to generate structured answers.

Beyond Classification: Financial Reasoning in State-of-the-Art Language Models

Large Language Models (LLMs), consisting of 100 billion or more parameters, have demonstrated remarkable ability in complex multi-step reasoning tasks. However, the application of such generic advancements has been limited to a few fields, such as clinical or legal, with the field of financial reasoning remaining largely unexplored. To the best of our knowledge, the ability of LLMs to solve financial reasoning problems has never been dealt with, and whether it can be performed at any scale remains unknown. To address this knowledge gap, this research presents a comprehensive investigation into the potential application of LLMs in the financial domain. The investigation includes a detailed exploration of a range of subjects, including task formulation, synthetic data generation, prompting methods, and evaluation capability. Furthermore, the study benchmarks various GPT variants with parameter scales ranging from 2.8B to 13B, with and without instruction tuning, on diverse dataset sizes. By analyzing the results, we reveal that the ability to generate coherent financial reasoning first emerges at 6B parameters, and continues to improve with better instruction-tuning or larger datasets. Additionally, the study provides a publicly accessible dataset named sFIOG (Synthetic-Financial Investment Opinion Generation), consisting of 11,802 synthetic investment thesis samples, to support further research in the field of financial reasoning. Overall, this research seeks to contribute to the understanding of the efficacy of language models in the field of finance, with a particular emphasis on their ability to engage in sophisticated reasoning and analysis within the context of investment decision-making.

Removing Non-Stationary Knowledge From Pre-Trained Language Models for Entity-Level Sentiment Classification in Finance

Extraction of sentiment signals from news text, stock message boards, and business reports, for stock movement prediction, has been a rising field of interest in finance. Building upon past literature, the most recent works attempt to better capture sentiment from sentences with complex syntactic structures by introducing aspect-level sentiment classification (ASC). Despite the growing interest, however, fine-grained sentiment analysis has not been fully explored in non-English literature due to the shortage of annotated finance-specific data. Accordingly, it is necessary for non-English languages to leverage datasets and pre-trained language models (PLM) of different domains, languages, and tasks to best their performance. To facilitate finance-specific ASC research in the Korean language, we build KorFinASC, a Korean aspect-level sentiment classification dataset for finance consisting of 12,613 human-annotated samples, and explore methods of intermediate transfer learning. Our experiments indicate that past research has been ignorant towards the potentially wrong knowledge of financial entities encoded during the training phase, which has overestimated the predictive power of PLMs. In our work, we use the term "non-stationary knowledge'' to refer to information that was previously correct but is likely to change, and present "TGT-Masking'', a novel masking pattern to restrict PLMs from speculating knowledge of the kind. Finally, through a series of transfer learning with TGT-Masking applied we improve 22.63% of classification accuracy compared to standalone models on KorFinASC.