Related papers: Evaluation Under Imperfect Benchmarks and Ratings:…

Existing frameworks for evaluating long-context language models (LCLM) can be broadly categorized into real-world applications (e.g, document summarization) and synthetic tasks (e.g, needle-in-a-haystack). Despite their utility, both…

Current measures for evaluating text simplification systems focus on evaluating lexical text aspects, neglecting its structural aspects. In this paper we propose the first measure to address structural aspects of text simplification, called…

Event extraction has gained considerable interest due to its wide-ranging applications. However, recent studies draw attention to evaluation issues, suggesting that reported scores may not accurately reflect the true performance. In this…

The rapid rise in popularity of Large Language Models (LLMs) with emerging capabilities has spurred public curiosity to evaluate and compare different LLMs, leading many researchers to propose their own LLM benchmarks. Noticing preliminary…

Usability evaluation is crucial in human-centered design but can be costly, requiring expert time and user compensation. In this work, we developed a method for synthetic heuristic evaluation using multimodal LLMs' ability to analyze images…

Large Language Models (LLMs) like GPT-4o can help automate text classification tasks at low cost and scale. However, there are major concerns about the validity and reliability of LLM outputs. By contrast, human coding is generally more…

The ability of large language models (LLMs) to interpret visual representations of data is crucial for advancing their application in data analysis and decision-making processes. This paper presents a novel synthetic dataset designed to…

Large Language Models (LLMs) effectiveness is usually evaluated by means of benchmarks such as MMLU, ARC-C, or HellaSwag, where questions are presented in their original wording, thus in a fixed, standardized format. However, real-world…

Evaluating statement autoformalization, translating natural language mathematics into formal languages like Lean 4, remains a significant challenge, with few metrics, datasets, and standards to robustly measure progress. In this work, we…

How much large language models (LLMs) can aid scientific discovery, notably in assisting academic peer review, is in heated debate. Between a literature digest and a human-comparable research assistant lies their practical application…

Large language models (LLMs) have shown remarkable capabilities in generating user summaries from a long list of raw user activity data. These summaries capture essential user information such as preferences and interests, and therefore are…

Evaluating large language models (LLMs) is challenging. Traditional ground-truth-based benchmarks fail to capture the comprehensiveness and nuance of real-world queries, while LLM-as-judge benchmarks suffer from grading biases and limited…

This paper investigates the ability of large language models (LLMs) to solve statistical tasks, as well as their capacity to assess the quality of reasoning. While state-of-the-art LLMs have demonstrated remarkable performance in a range of…

This paper introduces the Word Synchronization Challenge, a novel benchmark to evaluate large language models (LLMs) in Human-Computer Interaction (HCI). This benchmark uses a dynamic game-like framework to test LLMs ability to mimic human…

Lexical Simplification (LS) methods use a three-step pipeline: complex word identification, substitute generation, and substitute ranking, each with separate evaluation datasets. We found large language models (LLMs) can simplify sentences…

Existing automatic evaluation on text-to-image synthesis can only provide an image-text matching score, without considering the object-level compositionality, which results in poor correlation with human judgments. In this work, we propose…

Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation…

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components,…

Hallucinations are a key concern when creating applications that rely on Foundation models (FMs). Understanding where and how these subtle failures occur in an application relies on evaluation methods known as \textit{evals}. Prior work…

Large language models for code are advancing fast, yet our ability to evaluate them lags behind. Current benchmarks focus on narrow tasks and single metrics, which hide critical gaps in robustness, interpretability, fairness, efficiency,…