Conversational systems should generate diverse language forms to interact fluently and accurately. In this context, natural language generation (NLG) engines convert meaning representations (MRs) into sentences, directly influencing user perception. These MRs usually encode the communicative function (e.g., inform, request) via dialogue acts and enumerate the semantic content with slot–value pairs. In this work, our objective is to analyse whether providing a task demonstrator to the generator enhances the generated sentences of a fine-tuned model. This demonstrator is an MR–sentence pair extracted from the original dataset that enriches the input at training and inference time. The analysis involves five metrics that focus on different linguistic aspects and four datasets that differ in multiple features, such as domain, size or lexicon. All experiments are conducted with GPT-2 models, so the findings should be interpreted within this model family. To the best of our knowledge, this is the first study on dialogue NLG, implementing a comparative analysis of the impact of MRs on the generation quality across domains and corpus characteristics. Our key insight is that the proposed enriched inputs are effective for complex tasks and small datasets with high variability in MRs and sentences, and also for zero-shot settings. Moreover, the analysis of the metrics shows that the semantic metrics capture the generation quality more accurately than lexical metrics. In addition, those trained with human ratings can detect omissions and other subtle semantic issues. Finally, the evolution of the metric scores indicates that the generative models adapt quickly to different tasks.

What gives an automated judgment the authority to define a good answer? Large language models increasingly evaluate the outputs of other models, helping researchers compare systems, select training data, and inform deployment. However, agreement with human judgments cannot settle whose understanding of quality should guide these decisions. Automated evaluation can influence how quality itself is defined. When a rubric becomes a benchmark, a selection rule, or a training signal, its assumptions can become standards that others inherit. This piece develops bounded evaluative authority: reliance on an automated judgment should extend only to interpretations and decisions supported by evidence and accountable reasons within a stated scope. Drawing together measurement theory, evaluator research, and philosophical work on epistemic injustice, it distinguishes the ability to apply a criterion from the authority to choose it. Reliability, validity, and legitimacy address connected questions about consistency, meaning, and justified reliance. The discussion considers whose knowledge is recognised, who may resolve conflicting values, and when reasonable disagreement should remain visible rather than disappear into a single score. An Evaluative Authority Envelope makes the grounds of delegated judgment open to scrutiny. The argument extends earlier pieces in Responsible NLP on the limits of performance and the institutional distribution of responsibility. Its central claim is that responsible evaluation requires more than accurate scoring: it requires an account of why particular judgments should count, for whom, and with what possibility of challenge. A score can inform a decision; it cannot supply its own warrant to govern it.

The rapid spread of disinformation in the news poses a significant risk of negative consequences for society. As a result, detecting misleading news data has become a popular research topic. Correct news sentences often exhibit bias toward individuals, groups, or political parties or undergo alterations to convey specific moods or significance. The definition, annotation, and detection of problematic news sentences are immediate necessities. This research defines SEPSIS properties (SpEculation, oPinion, biaS, and tiwISt) of problematic news sentences. Sentences with any of these properties are referred to as Septic sentences. The current work automatically identifies Septic sentences in English news using deep learning models, namely convolutional neural networks (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), CNN-BiLSTM, and CNN-BiLSTM with an attention mechanism. Experimental results indicate that CNN-BiLSTM achieves the highest accuracy of 87.75% in identifying Septic sentences. We observe that Septic sentences contain problematic phrases that make them Septic, referred to as Septic phrases. There is an intent behind which the Septic statement is made. We used the conditional random fields (CRF) algorithm to identify Septic phrases and their corresponding intent, achieving 90.20% accuracy in phrase identification and 91.50% accuracy in intent identification. We conducted an ablation study to assess the importance of SEPSIS properties in fake news detection. Machine learning algorithms using Septic sentences as a feature performed about 1% better in fake news identification.