Here is today's selection of cs.CL papers exploring innovative approaches in NLP and privacy. The papers focus on improving the quality and trustworthiness of language model outputs, whether through mitigating hallucinations in summarization, enhancing the reliability of chatbot evaluations, or developing watermarking frameworks. Additionally, the research delves into resource-efficient training methods and examines privacy in text processing, reflecting a broad commitment to advancing both the efficacy and ethical use of language technologies.

Mitigating Hallucinations in Zero-Shot Scientific Summarisation: A Pilot Study

Large language models (LLMs) produce context inconsistency hallucinations, which are LLM generated outputs that are misaligned with the user prompt. This research project investigates whether prompt engineering (PE) methods can mitigate context inconsistency hallucinations in zero-shot LLM summarisation of scientific texts, where zero-shot indicates that the LLM relies purely on its pre-training data. Across eight yeast biotechnology research paper abstracts, six instruction-tuned LLMs were prompted with seven methods: a base- line prompt, two levels of increasing instruction complexity (PE-1 and PE-2), two levels of context repetition (CR-K1 and CR-K2), and two levels of random addition (RA-K1 and RA-K2). Context repetition involved the identification and repetition of K key sentences from the abstract, whereas random addition involved the repetition of K randomly selected sentences from the abstract, where K is 1 or 2. A total of 336 LLM-generated summaries were evaluated using six metrics: ROUGE-1, ROUGE-2, ROUGE-L, BERTScore, METEOR, and cosine similarity, which were used to compute the lexical and semantic alignment be- tween the summaries and the abstracts. Four hypotheses on the effects of prompt methods on summary alignment with the reference text were tested. Statistical analysis on 3744 collected datapoints was performed using bias-corrected and accelerated (BCa) bootstrap confidence intervals and Wilcoxon signed-rank tests with Bonferroni-Holm correction. The results demonstrated that CR and RA significantly improve the lexical alignment of LLM-generated summaries with the abstracts. These findings indicate that prompt engineering has the potential to impact hallucinations in zero-shot scientific summarisation tasks.

WaterSearch: A Quality-Aware Search-based Watermarking Framework for Large Language Models

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Existing approaches typically embed signals by manipulating token generation probabilities. Despite their effectiveness, these methods inherently face a trade-off between detectability and text quality: the signal strength and randomness required for robust watermarking tend to degrade the performance of downstream tasks. In this paper, we design a novel embedding scheme that controls seed pools to facilitate diverse parallel generation of watermarked text. Based on that scheme, we propose WaterSearch, a sentence-level, search-based watermarking framework adaptable to a wide range of existing methods. WaterSearch enhances text quality by jointly optimizing two key aspects: 1) distribution fidelity and 2) watermark signal characteristics. Furthermore, WaterSearch is complemented by a sentence-level detection method with strong attack robustness. We evaluate our method on three popular LLMs across ten diverse tasks. Extensive experiments demonstrate that our method achieves an average performance improvement of 51.01\% over state-of-the-art baselines at a watermark detectability strength of 95\%. In challenging scenarios such as short text generation and low-entropy output generation, our method yields performance gains of 47.78\% and 36.47\%, respectively. Moreover, under different attack senarios including insertion, synonym substitution and paraphrase attasks, WaterSearch maintains high detectability, further validating its robust anti-attack capabilities. Our code is available at \href{https://github.com/Yukang-Lin/WaterSearch}{https://github.com/Yukang-Lin/WaterSearch}.

Advancing Academic Chatbots: Evaluation of Non Traditional Outputs

Most evaluations of large language models focus on standard tasks such as factual question answering or short summarization. This research expands that scope in two directions: first, by comparing two retrieval strategies, Graph RAG, structured knowledge-graph based, and Advanced RAG, hybrid keyword-semantic search, for QA; and second, by evaluating whether LLMs can generate high quality non-traditional academic outputs, specifically slide decks and podcast scripts. We implemented a prototype combining Meta's LLaMA 3 70B open weight and OpenAI's GPT 4o mini API based. QA performance was evaluated using both human ratings across eleven quality dimensions and large language model judges for scalable cross validation. GPT 4o mini with Advanced RAG produced the most accurate responses. Graph RAG offered limited improvements and led to more hallucinations, partly due to its structural complexity and manual setup. Slide and podcast generation was tested with document grounded retrieval. GPT 4o mini again performed best, though LLaMA 3 showed promise in narrative coherence. Human reviewers were crucial for detecting layout and stylistic flaws, highlighting the need for combined human LLM evaluation in assessing emerging academic outputs.

Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy

Training models for Natural Language Processing (NLP) requires substantial computational resources and time, posing significant challenges, especially for NLP development in Bangla, where access to high-end hardware is often limited. In this work, we explore automatic mixed precision (AMP) training as a means to improve computational efficiency without sacrificing model performance. By leveraging a dynamic mix of 16-bit and 32-bit floating-point computations, AMP lowers GPU memory requirements and speeds up training without degrading model performance. We evaluate AMP across four standard Bangla NLP tasks, namely sentiment analysis, named entity recognition, error classification, and question answering, using four transformer-based models: BanglaBERT, BanglishBERT, XLM-R, and mBERT. Our results demonstrate that AMP accelerates training by 44.5% and reduces memory consumption by 17.6%, while maintaining F-1 score within 99.7% of the full-precision baselines. This empirical study highlights AMP's potential to democratize access to state-of-the-art NLP capabilities in hardware-constrained settings by lowering computational barriers.

How do we measure privacy in text? A survey of text anonymization metrics

In this work, we aim to clarify and reconcile metrics for evaluating privacy protection in text through a systematic survey. Although text anonymization is essential for enabling NLP research and model development in domains with sensitive data, evaluating whether anonymization methods sufficiently protect privacy remains an open challenge. In manually reviewing 47 papers that report privacy metrics, we identify and compare six distinct privacy notions, and analyze how the associated metrics capture different aspects of privacy risk. We then assess how well these notions align with legal privacy standards (HIPAA and GDPR), as well as user-centered expectations grounded in HCI studies. Our analysis offers practical guidance on navigating the landscape of privacy evaluation approaches further and highlights gaps in current practices. Ultimately, we aim to facilitate more robust, comparable, and legally aware privacy evaluations in text anonymization.