We examine evaluation of faithfulness to input data in the context of hotel highlights—brief LLM-generated summaries that capture unique features of accommodations. Through human evaluation campaigns involving categorical error assessment and span-level annotation, we compare traditional metrics, trainable methods, and LLM-as-a-judge approaches. Our findings reveal that simpler metrics like word overlap correlate surprisingly well with human judgments (r=0.63), often outperforming more complex methods when applied to out-of-domain data. We further demonstrate that while LLMs can generate high-quality highlights, they prove unreliable for evaluation as they tend to severely under- or over-annotate. Our analysis of real-world business impacts shows incorrect and non-checkable information pose the greatest risks. We also highlight challenges in crowdsourced evaluations.

We describe a reproduction of a human annotation experiment that was performed to evaluate the effectiveness of text style transfer systems (Reif et al., 2021). Despite our efforts to closely imitate the conditions of the original study, the results obtained differ significantly from those in the original study. We performed a statistical analysis of the results obtained, discussed the sources of these discrepancies in the study design, and quantified reproducibility. The reproduction followed the common approach to reproduction adopted by the ReproHum project.

Hallucinations are one of the most pressing challenges for large language models (LLMs). While numerous methods have been proposed to detect and mitigate them automatically, human evaluation continues to serve as the gold standard. However, these human evaluations of hallucinations show substantial variation in definitions, terminology, and evaluation practices. In this paper, we survey 64 studies involving human evaluation of hallucination published between 2019 and 2024, to investigate how hallucinations are currently defined and assessed. Our analysis reveals a lack of consistency in definitions and exposes several concerning methodological shortcomings. Crucial details, such as evaluation guidelines, user interface design, inter-annotator agreement metrics, and annotator demographics, are frequently under-reported or omitted altogether.

The WMT25 Multilingual Instruction Shared Task (MIST) introduces a benchmark to evaluate large language models (LLMs) across 30 languages. The benchmark covers five types of problems: machine translation, linguistic reasoning, open-ended generation, cross-lingual summarization, and LLM-as-a-judge.We provide automatic evaluation and collect human annotations, which highlight the limitations of automatic evaluation and allow further research into metric meta-evaluation. We run on our benchmark a diverse set of open- and closed-weight LLMs, providing a broad assessment of the multilingual capabilities of current LLMs. Results highlight substantial variation across sub-tasks and languages, revealing persistent challenges in reasoning, cross-lingual generation, and evaluation reliability. This work establishes a standardized framework for measuring future progress in multilingual LLM development.

Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regarding training data, has repeatedly raised concerns about data contamination among researchers. Several attempts have been made to address this issue, but they are limited to anecdotal evidence and trial and error. Additionally, they overlook the problem of indirect data leaking, where modelsare iteratively improved by using data coming from users. In this work, we conduct the first systematic analysis of work using OpenAI’s GPT-3.5 and GPT-4, the most prominently used LLMs today, in the context of data contamination. By analysing 255 papers and considering OpenAI’s data usage policy, we extensively document the amount of data leaked to these models during the first year after the model’s release. We report that these models have been globally exposed to ∼4.7M samples from 263 benchmarks. At the same time, we document a number of evaluation malpractices emerging in the reviewed papers, such as unfair or missing baseline comparisons and reproducibility issues. We release our results as a collaborative project on https://leak-llm.github.io/, where other researchers can contribute to our efforts.

In this paper, we describe several reproductions of a human evaluation experiment measuring the quality of automatic dialogue summarization (Feng et al., 2021). We investigate the impact of the annotators’ highest level of education, field of study, and native language on the evaluation of the informativeness of the summary. We find that the evaluation is relatively consistent regardless of these factors, but the biggest impact seems to be a prior specific background in natural language processing (as opposed to, e.g. a background in computer sci- ence). We also find that the experiment setup (asking for single vs. multiple criteria) may have an impact on the results.

Automatic metrics are extensively used to evaluate Natural Language Processing systems. However, there has been increasing focus on how the are used and reported by practitioners within the field. In this paper, we have conducted a survey on the use of automatic metrics, focusing particularly on natural language generation tasks. We inspect which metrics are used as well as why they are chosen and how their use is reported. Our findings from this survey reveal significant shortcomings, including inappropriate metric usage, lack of implementation details and missing correlations with human judgements. We conclude with recommendations that we believe authors should follow to enable more rigour within the field.

We present ‘factgenie‘: a framework for annotating and visualizing word spans in textual model outputs. Annotations can capture various span-based phenomena such as semantic inaccuracies or irrelevant text. With ‘factgenie‘, the annotations can be collected both from human crowdworkers and large language models. Our framework consists of a web interface for data visualization and gathering text annotations, powered by an easily extensible codebase.

In this position paper, I present my research interest in the faithfulness of natural language generation, i.e. the adherence to the data provided by a user or the dialog state. I motivate the task and present my progress and plans on the topic. I propose my position on the future of research dialog systems and share topics I would like to discuss during the roundtables.

With the fast-growing popularity of current large pre-trained language models (LLMs), it is necessary to dedicate efforts to making them more reliable. In this thesis proposal, we aim to improve the reliability of natural language generation systems (NLG) by researching the semantic accuracy of their outputs. We look at this problem from the outside (evaluation) and from the inside (interpretability). We propose a novel method for evaluating semantic accuracy and discuss the importance of working towards a unified and objective benchmark for NLG metrics. We also review interpretability approaches which could help us pinpoint the sources of inaccuracies within the models and explore potential mitigation strategies.

This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition. We present three different approaches to predicting turn-level qualities of chatbot responses based on large language models (LLMs). We report improvement over the baseline using dynamic few-shot examples from a vector store for the prompts for ChatGPT. We also analyze the performance of the other two approaches and report needed improvements for future work. We developed the three systems over just two weeks, showing the potential of LLMs for this task. An ablation study conducted after the challenge deadline shows that the new Llama 2 models are closing the performance gap between ChatGPT and open-source LLMs. However, we find that the Llama 2 models do not benefit from few-shot examples in the same way as ChatGPT.

We present a free online demo of THEaiTRobot, an open-source bilingual tool for interactively generating theatre play scripts, in two versions. THEaiTRobot 1.0 uses the GPT-2 language model with minimal adjustments. THEaiTRobot 2.0 uses two models created by fine-tuning GPT-2 on purposefully collected and processed datasets and several other components, generating play scripts in a hierarchical fashion (title → synopsis → script). The underlying tool is used in the THEaiTRE project to generate scripts for plays, which are then performed on stage by a professional theatre.

We experiment with adapting generative language models for the generation of long coherent narratives in the form of theatre plays. Since fully automatic generation of whole plays is not currently feasible, we created an interactive tool that allows a human user to steer the generation somewhat while minimizing intervention. We pursue two approaches to long-text generation: a flat generation with summarization of context, and a hierarchical text-to-text two-stage approach, where a synopsis is generated first and then used to condition generation of the final script. Our preliminary results and discussions with theatre professionals show improvements over vanilla language model generation, but also identify important limitations of our approach.