While the reasoning capabilities of Large Language Models (LLMs) excel in analytical tasks such as mathematics and code generation, their utility for abstractive summarization remains widely assumed but largely unverified. To bridge this gap, we first tailor general reasoning strategies to the summarization domain. We then conduct a systematic, large scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, assessing both summary quality and faithfulness. Our findings show that reasoning is not a universal solution and its effectiveness is highly dependent on the specific strategy and context. Specifically, we observe a trade-off between summary quality and factual faithfulness: explicit reasoning strategies tend to improve fluency at the expense of factual grounding, while implicit reasoning in LRMs exhibits the inverse pattern. Furthermore, increasing an LRM's internal reasoning budget does not improve, and can even hurt, factual consistency, suggesting that effective summarization demands faithful compression rather than creative over-thinking.

The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model (LLM) inference. However, this efficiency optimization introduces significant yet underexplored privacy risks. This paper provides the first comprehensive analysis of these vulnerabilities, demonstrating that an attacker can reconstruct sensitive user inputs directly from the KV-cache. We design and implement three distinct attack vectors: a direct Inversion Attack, a more broadly applicable and potent Collision Attack, and a semantic-based Injection Attack. These methods demonstrate the practicality and severity of KV-cache privacy leakage issues. To mitigate this, we propose KV-Cloak, a novel, lightweight, and efficient defense mechanism. KV-Cloak uses a reversible matrix-based obfuscation scheme, combined with operator fusion, to secure the KV-cache. Our extensive experiments show that KV-Cloak effectively thwarts all proposed attacks, reducing reconstruction quality to random noise. Crucially, it achieves this robust security with virtually no degradation in model accuracy and minimal performance overhead, offering a practical solution for trustworthy LLM deployment.

Despite Telugu being spoken by over 80 million people, speech translation research for this morphologically rich language remains severely underexplored. We address this gap by developing a high-quality Telugu--English speech translation benchmark from 46 hours of manually verified CSTD corpus data (30h/8h/8h train/dev/test split). Our systematic comparison of cascaded versus end-to-end architectures shows that while IndicWhisper + IndicMT achieves the highest performance due to extensive Telugu-specific training data, finetuned SeamlessM4T models demonstrate remarkable competitiveness despite using significantly less Telugu-specific training data. This finding suggests that with careful hyperparameter tuning and sufficient parallel data (potentially less than 100 hours), end-to-end systems can achieve performance comparable to cascaded approaches in low-resource settings. Our metric reliability study evaluating BLEU, METEOR, ChrF++, ROUGE-L, TER, and BERTScore against human judgments reveals that traditional metrics provide better quality discrimination than BERTScore for Telugu--English translation. The work delivers three key contributions: a reproducible Telugu--English benchmark, empirical evidence of competitive end-to-end performance potential in low-resource scenarios, and practical guidance for automatic evaluation in morphologically complex language pairs.

Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in high-stakes domains like clinical applications, where factual inaccuracies can have severe consequences. Existing evaluation metrics fail to adequately assess factual consistency and lack interpretability, making diagnosing and mitigating errors difficult. We propose an interpretable framework for factual consistency assessment for in-domain and open-domain texts to address these limitations. Our approach decomposes text into atomic facts and introduces a flexible, schema-free methodology. Unlike previous methods with an absolute metric, we incorporate a weighted metric to enhance factual evaluation. Additionally, we propose a mechanism to control assessment complexity in intricate domains. We benchmark our approach on popular general and clinical datasets and release our code to support fact-aware model training in future research.

Large language models (LLMs) are now used in settings such as Google's AI Overviews, where it summarizes multiple long documents. However, it remains unclear whether they weight all inputs equally. Focusing on abortion-related news, we construct 40 pro-neutral-con article triplets, permute each triplet into six input orders, and prompt Gemini 2.5 Flash to generate a neutral overview. We evaluate each summary against its source articles using ROUGE-L (lexical overlap), BERTScore (semantic similarity), and SummaC (factual consistency). One-way ANOVA reveals a significant primacy effect for BERTScore across all stances, indicating that summaries are more semantically aligned with the first-seen article. Pairwise comparisons further show that Position 1 differs significantly from Positions 2 and 3, while the latter two do not differ from each other, confirming a selective preference for the first document. The findings present risks for applications that rely on LLM-generated overviews and for agentic AI systems, where the steps involving LLMs can disproportionately influence downstream actions.

Large Language Models (LLMs) have proven efficient in giving definition-type answers to user input queries. While for humans giving various types of answers, such as examples and paraphrases, is an easy task, LLMs struggle to provide correct answers for other than definition-type queries. In this study, we evaluated this drop in performance using TrackList, a fine-grained linguistic and statistical analysis pipeline to investigate the impact of the pre-training data on LLMs answers to diverse linguistic queries. We also introduce RefoMed-EN, an English dataset consisting of 6170 human-annotated medical terms alongside their corresponding definitions, denominations, exemplifications, explanations, or paraphrases. We studied whether the high frequency of a concept (head) or low frequency (tail) impacts the language model's performance. We evaluated the quality of the LLM's output using syntactic and semantic similarity metrics, statistical correlations and embeddings. Results showed that the LLM's task performance for definition type questions is the highest, while for the exemplification type it is the lowest. Additionally, we showed that for definition-type questions, large language models are prone to paraphrase more on popular and frequent knowledge and less on tail and technical knowledge, especially in the expert texts.

Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular pipeline that reframes summarization as a semantic enrichment task. FRAME extracts and scores salient facts, organizes them thematically, and uses these to enrich an outline into an abstractive summary. To personalize summaries, we introduce SCOPE, a reason-out-loud protocol that has the model build a reasoning trace by answering nine questions before content selection. For evaluation, we propose P-MESA, a multi-dimensional, reference-free evaluation framework to assess if a summary fits a target reader. P-MESA reliably identifies error instances, achieving >= 89% balanced accuracy against human annotations and strongly aligns with human severity ratings (r >= 0.70). On QMSum and FAME, FRAME reduces hallucination and omission by 2 out of 5 points (measured with MESA), while SCOPE improves knowledge fit and goal alignment over prompt-only baselines. Our findings advocate for rethinking summarization to improve control, faithfulness, and personalization.

BERTScore has become a widely adopted metric for evaluating semantic similarity between natural language sentences. However, we identify a critical limitation: BERTScore exhibits low sensitivity to numerical variation, a significant weakness in finance where numerical precision directly affects meaning (e.g., distinguishing a 2% gain from a 20% loss). We introduce FinNuE, a diagnostic dataset constructed with controlled numerical perturbations across earnings calls, regulatory filings, social media, and news articles. Using FinNuE, demonstrate that BERTScore fails to distinguish semantically critical numerical differences, often assigning high similarity scores to financially divergent text pairs. Our findings reveal fundamental limitations of embedding-based metrics for finance and motivate numerically-aware evaluation frameworks for financial NLP.

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and injects them into LLMs' KV cache. Building on this representation, we employ a two-stage training paradigm: first locating a dedicated retrieval layer within the LLM, and then applying an attention-based loss at this layer to explicitly supervise attention toward relevant KB entries. Unlike traditional retrieval-augmented generation methods that rely heavily on the performance of external retrievers and multi-stage pipelines, SR-KI supports end-to-end inference by performing retrieval entirely within the model's latent space. This design enables efficient compression of injected knowledge and facilitates dynamic knowledge updates. Comprehensive experiments demonstrate that SR-KI enables the integration of up to 40K KBs into a 7B LLM on a single A100 40GB GPU, and achieves strong retrieval performance, maintaining over 98% Recall@10 on the best-performing task and exceeding 88% on average across all tasks. Task performance on question answering and KB ID generation also demonstrates that SR-KI maintains strong performance while achieving up to 99.75% compression of the injected KBs. Our code will be available at SR-KI.

Large Language Models (LLMs) are increasingly demonstrating the potential to reach human-level performance in generating clinical summaries from patient-clinician conversations. However, these summaries often focus on patients' biology rather than their preferences, values, wishes, and concerns. To achieve patient-centered care, we propose a new standard for Artificial Intelligence (AI) clinical summarization tasks: Patient-Centered Summaries (PCS). Our objective was to develop a framework to generate PCS that capture patient values and ensure clinical utility and to assess whether current open-source LLMs can achieve human-level performance in this task. We used a mixed-methods process. Two Patient and Public Involvement groups (10 patients and 8 clinicians) in the United Kingdom participated in semi-structured interviews exploring what personal and contextual information should be included in clinical summaries and how it should be structured for clinical use. Findings informed annotation guidelines used by eight clinicians to create gold-standard PCS from 88 atrial fibrillation consultations. Sixteen consultations were used to refine a prompt aligned with the guidelines. Five open-source LLMs (Llama-3.2-3B, Llama-3.1-8B, Mistral-8B, Gemma-3-4B, and Qwen3-8B) generated summaries for 72 consultations using zero-shot and few-shot prompting, evaluated with ROUGE-L, BERTScore, and qualitative metrics. Patients emphasized lifestyle routines, social support, recent stressors, and care values. Clinicians sought concise functional, psychosocial, and emotional context. The best zero-shot performance was achieved by Mistral-8B (ROUGE-L 0.189) and Llama-3.1-8B (BERTScore 0.673); the best few-shot by Llama-3.1-8B (ROUGE-L 0.206, BERTScore 0.683). Completeness and fluency were similar between experts and models, while correctness and patient-centeredness favored human PCS.