相关论文: Unveiling the Achilles' Heel of NLG Evaluators: A …

Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. However, recent studies reveal that the robustness of these…

As Large Language Models (LLMs) are pre-trained on ultra-large-scale corpora, the problem of data contamination is becoming increasingly serious, and there is a risk that static evaluation benchmarks overestimate the performance of LLMs. To…

The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…

The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and…

Large language models (LLMs) have significantly transformed the educational landscape. As current plagiarism detection tools struggle to keep pace with LLMs' rapid advancements, the educational community faces the challenge of assessing…

Deep learning models are susceptible to adversarial examples that have imperceptible perturbations in the original input, resulting in adversarial attacks against these models. Analysis of these attacks on the state of the art transformers…

Automatic evaluating the performance of Open-domain dialogue system is a challenging problem. Recent work in neural network-based metrics has shown promising opportunities for automatic dialogue evaluation. However, existing methods mainly…

Adversarial claim rewriting is widely used to test fact-checking systems, but standard metrics fail to capture truth-conditional consistency and often label semantically corrupted rewrites as successful. We introduce AtomEval, a…

We now have a rich and growing set of modeling tools and algorithms for inducing linguistic structure from text that is less than fully annotated. In this paper, we discuss some of the weaknesses of our current methodology. We present a new…

Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical…

Assessing Large Language Models'(LLMs) underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases. Nevertheless, current value measurement methods face the informativeness…

Despite remarkable advancements in mitigating hallucinations in large language models (LLMs) by retrieval augmentation, it remains challenging to measure the reliability of LLMs using static question-answering (QA) data. Specifically, given…

Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…

Large language models (LLMs) have shown remarkable performance on various tasks, but existing evaluation benchmarks are often static and insufficient to fully assess their robustness and generalization in realistic scenarios. Prior work…

We address a fundamental challenge in Natural Language Generation (NLG) model evaluation -- the design and evaluation of evaluation metrics. Recognizing the limitations of existing automatic metrics and noises from how current human…

Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency. However, automatic…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

Text evaluation has historically posed significant challenges, often demanding substantial labor and time cost. With the emergence of large language models (LLMs), researchers have explored LLMs' potential as alternatives for human…

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of…

The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs' values can help expose their misalignment, but relies on reference-free evaluators, e.g., fine-tuned LLMs or…