TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch

AI-generated fabricated scientific manuscripts raise growing concerns with large-scale breaches of academic integrity. In this work, we present the first systematic study on detecting AI-generated fabricated scientific tables in empirical NLP papers, as information in tables serve as critical evidence for claims. We construct FabTab, the first benchmark dataset of fabricated manuscripts with tables, comprising 1,173 AI-generated papers and 1,215 human-authored ones in empirical NLP. Through a comprehensive analysis, we identify systematic differences between fabricated and real tables and operationalize them into a set of discriminative features within the TAB-AUDIT framework. The key feature, within-table mismatch, captures the perplexity gap between a table's skeleton and its numerical content. Experimental results show that RandomForest built on these features significantly outperform prior state-of-the-art methods, achieving 0.987 AUROC in-domain and 0.883 AUROC out-of-domain. Our findings highlight experimental tables as a critical forensic signal for detecting AI-generated scientific fraud and provide a new benchmark for future research.

Resurfacing Paralinguistic Awareness in Large Audio Language Models

Large Audio Language Models (LALMs) have expanded the interaction with human to speech modality, which introduces great interactive potential, due to the paralinguistic cues implicitly indicating the user context. However, building on the current content-centred paradigm, LALMs usually neglect such paralinguistic cues and respond solely based on query content. In this work, to resurface the paralinguistic awareness in LALMs, we introduce five diverse layer-wise analyses to jointly identify paralinguistic layers and semantic understanding layers. Based on these insights, we propose a paralinguistic-enhanced fine-tuning (PE-FT) protocol accordingly to equip LALMs with paralinguistic-aware capabilities, including (1) selective-layer fine-tuning, and (2) an auxiliary dual-level classification head. Our experiments demonstrate that PE-FT protocol efficiently and effectively resurfaces the paralinguistic awareness, even surpassing the performance of the all-layer fine-tuning strategy.

LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations

Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator reliability. We introduce LiveCultureBench, a multi-cultural, dynamic benchmark that embeds LLMs as agents in a simulated town and evaluates them on both task completion and adherence to socio-cultural norms. The simulation models a small city as a location graph with synthetic residents having diverse demographic and cultural profiles. Each episode assigns one resident a daily goal while others provide social context. An LLM-based verifier generates structured judgments on norm violations and task progress, which we aggregate into metrics capturing task-norm trade-offs and verifier uncertainty. Using LiveCultureBench across models and cultural profiles, we study (i) cross-cultural robustness of LLM agents, (ii) how they balance effectiveness against norm sensitivity, and (iii) when LLM-as-a-judge evaluation is reliable for automated benchmarking versus when human oversight is needed.

ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis

While self-reflection can enhance language model reliability, its underlying mechanisms remain opaque, with existing analyses often yielding correlation-based insights that fail to generalize. To address this, we introduce \textbf{\texttt{ReBeCA}} (self-\textbf{\texttt{Re}}flection \textbf{\texttt{Be}}havior explained through \textbf{\texttt{C}}ausal \textbf{\texttt{A}}nalysis), a framework that unveils the interpretable behavioral hierarchy governing the self-reflection outcome. By modeling self-reflection trajectories as causal graphs, ReBeCA isolates genuine determinants of performance through a three-stage Invariant Causal Prediction (ICP) pipeline. We establish three critical findings: (1) \textbf{Behavioral hierarchy:} Semantic behaviors of the model influence final self-reflection results hierarchically: directly or indirectly; (2) \textbf{Causation matters:} Generalizability in self-reflection effects is limited to just a few semantic behaviors; (3) \textbf{More $\mathbf{\neq}$ better:} The confluence of seemingly positive semantic behaviors, even among direct causal factors, can impair the efficacy of self-reflection. ICP-based verification identifies sparse causal parents achieving up to $49.6\%$ structural likelihood gains, stable across tasks where correlation-based patterns fail. Intervention studies on novel datasets confirm these causal relationships hold out-of-distribution ($p = .013, η^2_\mathrm{p} = .071$). ReBeCA thus provides a rigorous methodology for disentangling genuine causal mechanisms from spurious associations in self-reflection dynamics.

Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation

Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignment, failing to replicate real-world dynamics in object motion. This limitation arises primarily from their reliance on learned statistical correlations rather than capturing mechanisms adhering to physical laws. To address this issue, we introduce a novel framework that integrates symbolic regression (SR) and trajectory-guided image-to-video (I2V) models for physics-grounded video forecasting. Our approach extracts motion trajectories from input videos, uses a retrieval-based pre-training mechanism to enhance symbolic regression, and discovers equations of motion to forecast physically accurate future trajectories. These trajectories then guide video generation without requiring fine-tuning of existing models. Evaluated on scenarios in Classical Mechanics, including spring-mass, pendulums, and projectile motions, our method successfully recovers ground-truth analytical equations and improves the physical alignment of generated videos over baseline methods.

DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement

Vision-Language Models (VLMs) now generate discourse-level, multi-sentence visual descriptions, challenging text scene graph parsers originally designed for single-sentence caption-to-graph mapping. Current approaches typically merge sentence-level parsing outputs for discourse input, often missing phenomena like cross-sentence coreference, resulting in fragmented graphs and degraded downstream VLM task performance. To address this, we introduce a new task, Discourse-level text Scene Graph parsing (DiscoSG), supported by our dataset DiscoSG-DS, which comprises 400 expert-annotated and 8,430 synthesised multi-sentence caption-graph pairs for images. Each caption averages 9 sentences, and each graph contains at least 3 times more triples than those in existing datasets. While fine-tuning large PLMs (i.e., GPT-4) on DiscoSG-DS improves SPICE by approximately 48% over the best sentence-merging baseline, high inference cost and restrictive licensing hinder its open-source use, and smaller fine-tuned PLMs struggle with complex graphs. We propose DiscoSG-Refiner, which drafts a base graph using one small PLM, then employs a second PLM to iteratively propose graph edits, reducing full-graph generation overhead. Using two Flan-T5-Base models, DiscoSG-Refiner still improves SPICE by approximately 30% over the best baseline while achieving 86 times faster inference than GPT-4. It also consistently improves downstream VLM tasks like discourse-level caption evaluation and hallucination detection. Code and data are available at: https://github.com/ShaoqLin/DiscoSG

Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models

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.

Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to insufficient safety-alignment. Despite advances in defence measures for text and vision LLMs, effective safety-alignment strategies and audio-safety dataset specifically targeting LALMs are notably absent. Meanwhile defence measures based on Supervised Fine-tuning (SFT) struggle to address safety improvement while avoiding over-rejection issues, significantly compromising helpfulness. In this work, we propose an unsupervised safety-fine-tuning strategy as remedy that reshapes model's representation space to enhance existing LALMs safety-alignment while balancing the risk of over-rejection. Our experiments, conducted across three generations of Qwen LALMs, demonstrate that our approach significantly improves LALMs safety under three modality input conditions (audio-text, text-only, and audio-only) while increasing over-rejection rate by only 0.88% on average. Warning: this paper contains harmful examples.

LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews

Peer review is a cornerstone of quality control in scientific publishing. With the increasing workload, the unintended use of `quick' heuristics, referred to as lazy thinking, has emerged as a recurring issue compromising review quality. Automated methods to detect such heuristics can help improve the peer-reviewing process. However, there is limited NLP research on this issue, and no real-world dataset exists to support the development of detection tools. This work introduces LazyReview, a dataset of peer-review sentences annotated with fine-grained lazy thinking categories. Our analysis reveals that Large Language Models (LLMs) struggle to detect these instances in a zero-shot setting. However, instruction-based fine-tuning on our dataset significantly boosts performance by 10-20 performance points, highlighting the importance of high-quality training data. Furthermore, a controlled experiment demonstrates that reviews revised with lazy thinking feedback are more comprehensive and actionable than those written without such feedback. We will release our dataset and the enhanced guidelines that can be used to train junior reviewers in the community. (Code available here: https://github.com/UKPLab/arxiv2025-lazy-review)

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment--factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca task (from 4.50 to 4.60), a 0.22 enhancement on the Just-eval benchmark (from 4.34 to 4.56), and a maximum improvement of 0.32 (from 3.53 to 3.85) on the MT-Bench dataset. We release the code and data at https://github.com/AnonymousCode-ComputerScience/RIDE.