We develop a voice phishing (VP) detector by fine-tuning Llama3, a representative open-source, small language model (LM). In the prompt, we provide carefully-designed VP evaluation criteria and apply the Chain-of-Thought (CoT) technique. To evaluate the robustness of LMs and highlight differences in their performance, we construct an adversarial test dataset that places the models under challenging conditions. Moreover, to address the lack of VP transcripts, we create transcripts by referencing existing or new types of VP techniques. We compare cases where evaluation criteria are included, the CoT technique is applied, or both are used together. In the experiment, our results show that the Llama3-8B model, fine-tuned with a dataset that includes a prompt with VP evaluation criteria, yields the best performance among small LMs and is comparable to that of a GPT-4-based VP detector. These findings indicate that incorporating human expert knowledge into the prompt is more effective than using the CoT technique for small LMs in VP detection.

Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15\% of the generated scripts still fail to execute, even after supervised fine-tuning and reinforcement learning. We investigate whether this persistent error rate stems from model limitations or from reliance on a single-prompt design. To explore this, we propose a lightweight multi-agent pipeline that separates drafting, execution, repair, and judgment, using only an off-the-shelf GPT-4o-mini model. On the \textsc{Text2Chart31} benchmark, our system reduces execution errors to 4.5\% within three repair iterations, outperforming the strongest fine-tuned baseline by nearly 5 percentage points while requiring significantly less compute. Similar performance is observed on the \textsc{ChartX} benchmark, with an error rate of 4.6\%, demonstrating strong generalization. Under current benchmarks, execution success appears largely solved. However, manual review reveals that 6 out of 100 sampled charts contain hallucinations, and an LLM-based accessibility audit shows that only 33.3\% (\textsc{Text2Chart31}) and 7.2\% (\textsc{ChartX}) of generated charts satisfy basic colorblindness guidelines. These findings suggest that future work should shift focus from execution reliability toward improving chart aesthetics, semantic fidelity, and accessibility.

Online video web content is richly multimodal: a single video blends vision, speech, ambient audio, and on-screen text. Retrieval systems typically treat these modalities as independent retrieval sources, which can lead to noisy and subpar retrieval. We explore multimodal video content retrieval, where relevance can be scored from one particular modality or jointly across multiple modalities simultaneously. Consequently, an effective retriever must dynamically choose which modality (or set of modalities) best addresses the query. We introduce CLaMR, a multimodal, late-interaction retriever that jointly indexes 4 modalities: video frames, transcribed speech, on-screen text, and metadata. CLaMR jointly encodes all modalities with a unified multimodal backbone for improved contextualization and is trained to enhance dynamic modality selection via two key innovations. First, given the lack of training data for multimodal retrieval, we introduce MultiVENT 2.0++, a large-scale synthetic training dataset built on MultiVENT 2.0 (event-centric videos in various languages paired with queries) with modality-targeted queries. Next, we propose a modality-aware loss that jointly trains according to a standard contrastive objective alongside an objective for learning correct modality usage. On the test sets of MultiVENT 2.0++ and MSRVTT, conventional aggregation strategies, such as averaging similarities for baseline retrievers, degrade performance by introducing noise from irrelevant modalities. In contrast, CLaMR consistently outperforms existing retrievers: on MultiVENT 2.0++, CLaMR improves nDCG@10 by 25.6 over the best single-modality retriever and by 35.4 over the best multi-modality retriever. We illustrate CLaMR's downstream utility on long-video QA, retrieving relevant frames and obtaining a 3.50% boost over LanguageBind on Video-MME and 1.42% over dense sampling on LongVideoBench.

Table reasoning (TR) requires structured reasoning over semi-structured tabular data and remains challenging, particularly for small language models (SLMs, e.g., LLaMA-8B) due to their limited capacity compared to large LMs (LLMs, e.g., GPT-4o). To narrow this gap, we explore program-based TR (P-TR), which circumvents key limitations of text-based TR (T-TR), notably in numerical reasoning, by generating executable programs. However, applying P-TR to SLMs introduces two challenges: (i) vulnerability to heterogeneity in table layouts, and (ii) inconsistency in reasoning due to limited code generation capability. We propose Table-r1, a two-stage P-TR method designed for SLMs. Stage 1 introduces an innovative self-supervised learning task, Layout Transformation Inference, to improve tabular layout generalization from a programmatic view. Stage 2 adopts a mix-paradigm variant of Group Relative Policy Optimization, enhancing P-TR consistency while allowing dynamic fallback to T-TR when needed. Experiments on four TR benchmarks demonstrate that Table-r1 outperforms all SLM-based methods, achieving at least a 15% accuracy improvement over the base model (LLaMA-8B) across all datasets and reaching performance competitive with LLMs.

Natural Language Inference (NLI) is the task of determining whether a sentence pair represents entailment, contradiction, or a neutral relationship. While NLI models perform well on many inference tasks, their ability to handle fine-grained pragmatic inferences, particularly presupposition in conditionals, remains underexplored. In this study, we introduce CONFER, a novel dataset designed to evaluate how NLI models process inference in conditional sentences. We assess the performance of four NLI models, including two pre-trained models, to examine their generalization to conditional reasoning. Additionally, we evaluate Large Language Models (LLMs), including GPT-4o, LLaMA, Gemma, and DeepSeek-R1, in zero-shot and few-shot prompting settings to analyze their ability to infer presuppositions with and without prior context. Our findings indicate that NLI models struggle with presuppositional reasoning in conditionals, and fine-tuning on existing NLI datasets does not necessarily improve their performance.

We introduce ROLL, an efficient, scalable, and user-friendly library designed for Reinforcement Learning Optimization for Large-scale Learning. ROLL caters to three primary user groups: tech pioneers aiming for cost-effective, fault-tolerant large-scale training, developers requiring flexible control over training workflows, and researchers seeking agile experimentation. ROLL is built upon several key modules to serve these user groups effectively. First, a single-controller architecture combined with an abstraction of the parallel worker simplifies the development of the training pipeline. Second, the parallel strategy and data transfer modules enable efficient and scalable training. Third, the rollout scheduler offers fine-grained management of each sample's lifecycle during the rollout stage. Fourth, the environment worker and reward worker support rapid and flexible experimentation with agentic RL algorithms and reward designs. Finally, AutoDeviceMapping allows users to assign resources to different models flexibly across various stages.

Large Language Models (LLMs) have shown strong performance on NLP classification tasks. However, they typically rely on aggregated labels-often via majority voting-which can obscure the human disagreement inherent in subjective annotations. This study examines whether LLMs can capture multiple perspectives and reflect annotator disagreement in subjective tasks such as hate speech and offensive language detection. We use in-context learning (ICL) in zero-shot and few-shot settings, evaluating four open-source LLMs across three label modeling strategies: aggregated hard labels, and disaggregated hard and soft labels. In few-shot prompting, we assess demonstration selection methods based on textual similarity (BM25, PLM-based), annotation disagreement (entropy), a combined ranking, and example ordering strategies (random vs. curriculum-based). Results show that multi-perspective generation is viable in zero-shot settings, while few-shot setups often fail to capture the full spectrum of human judgments. Prompt design and demonstration selection notably affect performance, though example ordering has limited impact. These findings highlight the challenges of modeling subjectivity with LLMs and the importance of building more perspective-aware, socially intelligent models.

In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we tune a model by having it interact with a database engine? We frame this problem as a reinforcement learning problem where the model receives execution-based feedback from the environment in the form of scalar rewards. These rewards penalize execution failures and assign positive values when a query returns a correct answer. We use the rewards within the Group Relative Policy Optimization (GRPO) framework. We use a tabular reasoning benchmark to test and evaluate our findings. We find that with only weak supervision in the form of question-answer pairs, RL-tuning improves the accuracy of model generated SQL code from 31.49 to 49.83 while reducing error percentage from 25.43% to 14.71%. This improvement allowed the model nearly match the performance performance to the larger SQLCoder-70B model. Our work demonstrates the potential of using execution-based feedback to improve symbolic reasoning capabilities of LLMs.

Federated fine-tuning of large language models (FedLLMs) presents a promising approach for achieving strong model performance while preserving data privacy in sensitive domains. However, the inherent memorization ability of LLMs makes them vulnerable to training data extraction attacks. To investigate this risk, we introduce simple yet effective extraction attack algorithms specifically designed for FedLLMs. In contrast to prior "verbatim" extraction attacks, which assume access to fragments from all training data, our approach operates under a more realistic threat model, where the attacker only has access to a single client's data and aims to extract previously unseen personally identifiable information (PII) from other clients. This requires leveraging contextual prefixes held by the attacker to generalize across clients. To evaluate the effectiveness of our approaches, we propose two rigorous metrics-coverage rate and efficiency-and extend a real-world legal dataset with PII annotations aligned with CPIS, GDPR, and CCPA standards, achieving 89.9% human-verified precision. Experimental results show that our method can extract up to 56.57% of victim-exclusive PII, with "Address," "Birthday," and "Name" being the most vulnerable categories. Our findings underscore the pressing need for robust defense strategies and contribute a new benchmark and evaluation framework for future research in privacy-preserving federated learning.

Large Language Models (LLMs) have revolutionized Natural Language Processing by excelling at interpreting, reasoning about, and generating human language. However, their reliance on large-scale, often proprietary datasets poses a critical challenge: unauthorized usage of such data can lead to copyright infringement and significant financial harm. Existing dataset-inference methods typically depend on log probabilities to detect suspicious training material, yet many leading LLMs have begun withholding or obfuscating these signals. This reality underscores the pressing need for label-only approaches capable of identifying dataset membership without relying on internal model logits. We address this gap by introducing CatShift, a label-only dataset-inference framework that capitalizes on catastrophic forgetting: the tendency of an LLM to overwrite previously learned knowledge when exposed to new data. If a suspicious dataset was previously seen by the model, fine-tuning on a portion of it triggers a pronounced post-tuning shift in the model's outputs; conversely, truly novel data elicits more modest changes. By comparing the model's output shifts for a suspicious dataset against those for a known non-member validation set, we statistically determine whether the suspicious set is likely to have been part of the model's original training corpus. Extensive experiments on both open-source and API-based LLMs validate CatShift's effectiveness in logit-inaccessible settings, offering a robust and practical solution for safeguarding proprietary data.