Rethinking Generative Large Language Model Evaluation for Semantic Comprehension

• URL: http://arxiv.org/abs/2403.07872v1
• Date: Tue, 12 Mar 2024 17:59:48 GMT
• Title: Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
• Abstract summary: This paper revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for straightforward accuracy measurement. We introduce an RWQ-Elo rating system, engaging 24 large language models (LLMs) in a two-player competitive format, with GPT-4 serving as the judge. This system is designed to mirror real-world usage, and for this purpose, we have compiled a new benchmark called Real-world questions'' (RWQ) Our analysis reveals the stability of our RWQ-Elo system, the feasibility of registering new models, and its potential to
• Score: 27.21438605541497
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their sophisticated capabilities, large language models (LLMs) encounter a major hurdle in effective assessment. This paper first revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for straightforward accuracy measurement. Through a comprehensive evaluation of 24 models across 11 benchmarks, we highlight several potential drawbacks of MCQA, for instance, the inconsistency between the MCQA evaluation and the generation of open-ended responses in practical scenarios. In response, we introduce an RWQ-Elo rating system, engaging 24 LLMs such as GPT-4, GPT-3.5, Google-Gemini-Pro and LLaMA-1/-2, in a two-player competitive format, with GPT-4 serving as the judge. Each LLM receives an Elo rating thereafter. This system is designed to mirror real-world usage, and for this purpose, we have compiled a new benchmark called ``Real-world questions'' (RWQ), comprising 20,772 authentic user inquiries. Additionally, we thoroughly analyze the characteristics of our system and compare it with prior leaderboards like AlpacaEval and MT-Bench. Our analysis reveals the stability of our RWQ-Elo system, the feasibility of registering new models, and its potential to reshape LLM leaderboards.

Related papers

• LLM-as-a-Judge for Evaluating System Responses in Conversational Music Recommendation [20.276417246845593]
  We present the first user study to empirically assess the reliability of LLM-as-a-judge for evaluating CRS responses.<n>We collect $n=400$ ratings from 20 domain-expert annotators, who evaluate each response across two dimensions: Personalization Quality and Explanation Quality.<n>We find that LLM-based judges exhibit moderate positive alignment with human assessments and outperform all reference-based baselines.
  arXiv  Detail & Related papers  (2026-07-28T12:26:55Z)
• The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality [70.45240108873001]
  The FACTS Leaderboard is an online leaderboard suite that comprehensively evaluates the ability of language models to generate factually accurate text.<n>The suite provides a holistic measure of factuality by aggregating the performance of models on four distinct sub-leaderboards.
  arXiv  Detail & Related papers  (2025-12-11T16:35:14Z)
• ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering [38.045885431565345]
  We introduce ReTraceQA, a novel benchmark that introduces process-level evaluation for commonsense reasoning tasks.<n>Our expert-annotated dataset reveals that in a substantial portion of instances (14-24%), SLMs provide correct final answers despite flawed reasoning processes.
  arXiv  Detail & Related papers  (2025-10-10T13:03:33Z)
• Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models [7.232383381822326]
  We propose a scalable, modular framework for generating multiple-choice question-answering benchmarks.<n>Our pipeline automates every stage of MCQA creation, including PDF parsing, semantic chunking, question generation, and model evaluation.<n>We find that reasoning-trace retrieval consistently improves performance on both synthetic and expert-annotated benchmarks.
  arXiv  Detail & Related papers  (2025-09-12T23:22:49Z)
• AHELM: A Holistic Evaluation of Audio-Language Models [78.20477815156484]
  multimodal audio-language models (ALMs) take interleaved audio and text as input and output text.<n>AHELM is a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE and CoRe-Bench.<n>We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models.
  arXiv  Detail & Related papers  (2025-08-29T07:40:39Z)
• Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering [78.89231943329885]
  One of the most widely used tasks to evaluate Large Language Models (LLMs) is Multiple-Choice Question Answering (MCQA) In this work, we shed light on the inconsistencies of MCQA evaluation strategies, which can lead to inaccurate and misleading model comparisons.
  arXiv  Detail & Related papers  (2025-03-19T08:45:03Z)
• Judging the Judges: A Collection of LLM-Generated Relevance Judgements [37.103230004631996]
  This paper benchmarks and reports on the results of a large-scale automatic relevance judgment evaluation, the LLMJudge challenge at SIGIR 2024.<n>We release and benchmark 42 LLM-generated labels of the TREC 2023 Deep Learning track relevance judgments produced by eight international teams.
  arXiv  Detail & Related papers  (2025-02-19T17:40:32Z)
• CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution [74.41064280094064]
  textbfJudger-1 is the first open-source textbfall-in-one judge LLM. CompassJudger-1 is a general-purpose LLM that demonstrates remarkable versatility. textbfJudgerBench is a new benchmark that encompasses various subjective evaluation tasks.
  arXiv  Detail & Related papers  (2024-10-21T17:56:51Z)
• MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models [71.36392373876505]
  We introduce MMIE, a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs) MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts. It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies.
  arXiv  Detail & Related papers  (2024-10-14T04:15:00Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors [64.9938658716425]
  Existing evaluations of large language models' (LLMs) ability to recognize and reject unsafe user requests face three limitations. First, existing methods often use coarse-grained of unsafe topics, and are over-representing some fine-grained topics. Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations. Third, existing evaluations rely on large LLMs for evaluation, which can be expensive.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• Can multiple-choice questions really be useful in detecting the abilities of LLMs? [15.756543037102256]
  Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) The misalignment between the task and the evaluation method demands a thoughtful analysis of MCQ's efficacy. We evaluate nine LLMs on four question-answering (QA) datasets in two languages: Chinese and English.
  arXiv  Detail & Related papers  (2024-03-26T14:43:48Z)
• SEED-Bench-2: Benchmarking Multimodal Large Language Models [67.28089415198338]
  Multimodal large language models (MLLMs) have recently demonstrated exceptional capabilities in generating not only texts but also images given interleaved multimodal inputs. SEED-Bench-2 comprises 24K multiple-choice questions with accurate human annotations, which spans 27 dimensions. We evaluate the performance of 23 prominent open-source MLLMs and summarize valuable observations.
  arXiv  Detail & Related papers  (2023-11-28T05:53:55Z)
• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models [66.12432440863816]
  We propose Prometheus, a fully open-source Large Language Model (LLM) that is on par with GPT-4's evaluation capabilities. Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics. Prometheus achieves the highest accuracy on two human preference benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:50:08Z)
• Split and Merge: Aligning Position Biases in Large Language Model based Evaluators [23.38206418382832]
  PORTIA is an alignment-based system designed to mimic human comparison strategies to calibrate position bias. Our results show that PORTIA markedly enhances the consistency rates for all the models and comparison forms tested. It rectifies around 80% of the position bias instances within the GPT-4 model, elevating its consistency rate up to 98%.
  arXiv  Detail & Related papers  (2023-09-29T14:38:58Z)
• SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension [27.53415400454066]
  We introduce a benchmark named SEED-Bench to assess generative models. SEED-Bench consists of 19K multiple choice questions with accurate human annotations. We evaluate the performance of 18 models across all 12 dimensions, covering both the spatial and temporal understanding.
  arXiv  Detail & Related papers  (2023-07-30T04:25:16Z)
• Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization [66.08074487429477]
  We investigate the stability and reliability of large language models (LLMs) as automatic evaluators for abstractive summarization. We find that while ChatGPT and GPT-4 outperform the commonly used automatic metrics, they are not ready as human replacements.
  arXiv  Detail & Related papers  (2023-05-22T14:58:13Z)
• A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge [8.656503175492375]
  This paper presents the participation of NetEase Game AI Lab team for the ClariQ challenge at Search-oriented Conversational AI (SCAI) EMNLP workshop in 2020. The challenge asks for a complete conversational information retrieval system that can understanding and generating clarification questions. We propose a clarifying question selection system which consists of response understanding, candidate question recalling and clarifying question ranking.
  arXiv  Detail & Related papers  (2020-10-27T11:22:53Z)

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.