Watermarking generative-AI systems, such as LLMs, has gained considerable interest, driven by their enhanced capabilities across a wide range of tasks. Although current approaches have demonstrated that small, context-dependent shifts in the word distributions can be used to apply and detect watermarks, there has been little work in analyzing the impact that these perturbations have on the quality of generated texts. Balancing high detectability with minimal performance degradation is crucial in terms of selecting the appropriate watermarking setting; therefore this paper proposes a simple analysis framework where comparative assessment, a flexible NLG evaluation framework, is used to assess the quality degradation caused by a particular watermark setting. We demonstrate that our framework provides easy visualization of the quality-detection trade-off of watermark settings, enabling a simple solution to find an LLM watermark operating point that provides a well-balanced performance. This approach is applied to two different summarization systems and a translation system, enabling cross-model analysis for a task, and cross-task analysis.
Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks. One example is permutation sensitivity, where LLMs' outputs may significantly vary depending on the order of the input options. While debiasing techniques can mitigate these issues, and yield better performance and reliability, they often come with a high computational cost at inference. This paper addresses this inefficiency at inference time. The aim is to distill the capabilities of a computationally intensive, debiased, teacher model into a more compact student model. We explore two variants of student models: one based on pure distillation, and the other on an error-correction approach for more complex tasks, where the student corrects a single biased decision from the teacher to achieve a debiased output. Our approach is general and can be applied to both black-box and white-box LLMs. Furthermore, we demonstrate that our compact, encoder-only student models can outperform their larger, biased teacher counterparts, achieving better results with significantly fewer parameters.
Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. However, there has been significantly less work on the zero-shot abilities of ASR foundation models, with these systems typically fine-tuned to specific tasks or constrained to applications that match their training criterion and data annotation. In this work we investigate the ability of Whisper and MMS, ASR foundation models trained primarily for speech recognition, to perform zero-shot audio classification. We use simple template-based text prompts at the decoder and use the resulting decoding probabilities to generate zero-shot predictions. Without training the model on extra data or adding any new parameters, we demonstrate that Whisper shows promising zero-shot classification performance on a range of 8 audio-classification datasets, outperforming existing state-of-the-art zero-shot baseline's accuracy by an average of 9%. One important step to unlock the emergent ability is debiasing, where a simple unsupervised reweighting method of the class probabilities yields consistent significant performance gains. We further show that performance increases with model size, implying that as ASR foundation models scale up, they may exhibit improved zero-shot performance.
Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar when speaking. This process usually relies on a cascaded pipeline comprising an ASR system, disfluency removal, and GEC, with the associated concern of propagating errors between these individual modules. In this paper, we introduce an alternative "end-to-end" approach to spoken GEC, exploiting a speech recognition foundation model, Whisper. This foundation model can be used to replace the whole framework or part of it, e.g., ASR and disfluency removal. These end-to-end approaches are compared to more standard cascaded approaches on the data obtained from a free-speaking spoken language assessment test, Linguaskill. Results demonstrate that end-to-end spoken GEC is possible within this architecture, but the lack of available data limits current performance compared to a system using large quantities of text-based GEC data. Conversely, end-to-end disfluency detection and removal, which is easier for the attention-based Whisper to learn, does outperform cascaded approaches. Additionally, the paper discusses the challenges of providing feedback to candidates when using end-to-end systems for spoken GEC.
The Multimodal Video Search by Examples (MVSE) project investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content, topic, and emotion. A key element for this process is highly rapid, flexible, search to support large archives, which in MVSE is facilitated by representing video attributes by embeddings. This work aims to mitigate any performance loss from this rapid archive search by examining reranking approaches. In particular, zero-shot reranking methods using large language models are investigated as these are applicable to any video archive audio content. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus. Results demonstrate that reranking can achieve improved retrieval ranking without the need for any task-specific training data.
Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performance, with semantically equivalent settings often showing notable performance difference. This discrepancy can be partly attributed to word biases, where the classifier may be biased towards classes. To address this problem, it is possible to optimise classification thresholds on a labelled data set, however, this mitigates some of the advantages of prompt-based classifiers. This paper instead approaches this problem by examining the expected marginal probabilities of the classes. Here, probabilities are reweighted to have a uniform prior over classes, in an unsupervised fashion. Further, we draw a theoretical connection between the class priors and the language models' word prior, and offer the ability to set a threshold in a zero-resource fashion. We show that matching class priors correlates strongly with the oracle upper bound performance and demonstrate large consistent performance gains for prompt settings over a range of NLP tasks.
Evaluating Natural Language Generation (NLG) outputs is crucial but laborious and expensive. While various automatic NLG assessment methods have been proposed, they often are quite task-specific and have to be engineered with a particular domain and attribute in mind. In this work, we propose a robust zero-shot approach to NLG evaluation using pairwise comparative judgment with open-source Large Language Models (LLMs). The motivation for this approach is that even as humans, it is easier to determine which of two options are better, than it is to independently objectively score each option. We use this insight and leverage the emergent abilities of LLMs, where we probe FlanT5 to determine which of two candidate responses is better, rather than assigning absolute scores. Our results demonstrate that comparative assessment is a more effective approach than absolute scoring, enabling smaller open-source LLMs to achieve comparable performance to larger public access APIs. We evaluate systems on both summary evaluation and dialogue response generation, and show that opensource LLMs can lead to good correlations with human scores for a range of different attributes.
A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is designed to be human readable, punctuation is added, numbers are presented in Arabic numeric form and abbreviations are included. Additionally, these models have a tendency to skip disfluencies and hesitations in the output. Though useful for readability, these attributes are not helpful for assessing the ability of a candidate and providing feedback. Here a precise transcription of what a candidate said is needed. In this paper, we give a detailed analysis of Whisper outputs and propose two solutions: fine-tuning and soft prompt tuning. Experiments are conducted on both public speech corpora and an English learner dataset. Results show that we can effectively alter the decoding behaviour of Whisper to generate the exact words spoken in the response.
Multiple Choice examinations are a ubiquitous form of assessment that is used to measure the ability of candidates across various domains and tasks. Maintaining the quality of proposed questions is of great importance to test designers, and therefore newly proposed questions go through several pre-test evaluation stages before they can be deployed into real-world exams. This process is currently quite manual, which can lead to time lags in the question development cycle. Automating this process would lead to a large improvement in efficiency, however, current datasets do not contain sufficient pre-test analysis information. In this paper, we introduce CamChoice; a multiple-choice comprehension dataset with questions at different target levels, where questions have the true candidate selected options distributions. We introduce the task of candidate distribution matching, propose several evaluation metrics for the task, and demonstrate that automatic systems trained on RACE++ can be leveraged as baselines for our task. We further demonstrate that these automatic systems can be used for practical pre-test evaluation tasks such as detecting underperforming distractors, where our detection systems can automatically identify poor distractors that few candidates select. We release the data publicly for future research.
As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than having direct access to models themselves. In this scenario it is challenging to adapt systems to a specific target domain. To address this problem we consider the recently released OpenAI Whisper ASR as an example of a large-scale ASR system to assess adaptation methods. An error correction based approach is adopted, as this does not require access to the model, but can be trained from either 1-best or N-best outputs that are normally available via the ASR API. LibriSpeech is used as the primary target domain for adaptation. The generalization ability of the system in two distinct dimensions are then evaluated. First, whether the form of correction model is portable to other speech recognition domains, and secondly whether it can be used for ASR models having a different architecture.