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

• URL: http://arxiv.org/abs/2409.11239v2
• Date: Wed, 2 Oct 2024 11:07:14 GMT
• Title: LLM-as-a-Judge & Reward Model: What They Can and Cannot Do
• Authors: Guijin Son, Hyunwoo Ko, Hoyoung Lee, Yewon Kim, Seunghyeok Hong,
• Abstract summary: We conduct a comprehensive analysis of automated evaluators, reporting several key findings on their behavior. We discover that English evaluation capabilities significantly influence language-specific evaluation capabilities, enabling evaluators trained in English to easily transfer their skills to other languages. We find that state-of-the-art evaluators struggle with challenging prompts, in either English or Korean, underscoring their limitations in assessing or generating complex reasoning questions.
• Score: 2.2469442203227863
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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 in diverse contexts, such as non-English prompts, factual verification, or challenging questions, remains unexplored. In this paper, we conduct a comprehensive analysis of automated evaluators, reporting several key findings on their behavior. First, we discover that English evaluation capabilities significantly influence language-specific evaluation 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 find that state-of-the-art evaluators struggle with challenging prompts, in either English or Korean, underscoring their limitations in assessing or generating complex reasoning questions. We release the dataset and codes used.

Related papers

• Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs [36.30321941154582]
  Hercule is a cross-lingual evaluation model that learns to assign scores to responses based on easily available reference answers in English. This study is the first comprehensive examination of cross-lingual evaluation using LLMs, presenting a scalable and effective approach for multilingual assessment.
  arXiv  Detail & Related papers  (2024-10-17T09:45:32Z)
• How Does Quantization Affect Multilingual LLMs? [50.867324914368524]
  Quantization techniques are widely used to improve inference speed and deployment of large language models. We conduct a thorough analysis of quantized multilingual LLMs, focusing on performance across languages and at varying scales.
  arXiv  Detail & Related papers  (2024-07-03T15:39:40Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts. We find that Llama Instruct and Mistral models exhibit high degrees of language confusion. We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Pragmatic Competence Evaluation of Large Language Models for the Korean Language [0.6757476692230009]
  This study evaluates how well Large Language Models (LLMs) understand context-dependent expressions from a pragmatic standpoint, specifically in Korean. We use both Multiple-Choice Questions (MCQs) for automatic evaluation and Open-Ended Questions (OEQs) assessed by human experts.
  arXiv  Detail & Related papers  (2024-03-19T12:21:20Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages [51.301942056881146]
  We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) We examine cross-lingual reranking with queries in English and passages in the African languages.
  arXiv  Detail & Related papers  (2023-12-26T18:38:54Z)
• Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models [51.75805497456226]
  This work focuses on the factual consistency issue with the help of the dialogue summarization task. Our evaluation shows that, on average, 26.8% of the summaries generated by LLMs contain factual inconsistency. To stimulate and enhance the dialogue comprehension ability of LLMs, we propose a fine-tuning paradigm with auto-constructed multi-task data.
  arXiv  Detail & Related papers  (2023-11-13T09:32:12Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Towards LLM-based Autograding for Short Textual Answers [4.853810201626855]
  This manuscript is an evaluation of a large language model for the purpose of autograding. Our findings suggest that while "out-of-the-box" LLMs provide a valuable tool, their readiness for independent automated grading remains a work in progress.
  arXiv  Detail & Related papers  (2023-09-09T22:25:56Z)
• Spoken Language Intelligence of Large Language Models for Language Learning [3.5924382852350902]
  We focus on evaluating the efficacy of large language models (LLMs) in the realm of education. We introduce a new multiple-choice question dataset to evaluate the effectiveness of LLMs in the aforementioned scenarios. We also investigate the influence of various prompting techniques such as zero- and few-shot method. We find that models of different sizes have good understanding of concepts in phonetics, phonology, and second language acquisition, but show limitations in reasoning for real-world problems.
  arXiv  Detail & Related papers  (2023-08-28T12:47:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.