Coral reefs are vital yet vulnerable ecosystems that require continuous monitoring to support conservation. While coral reef images provide essential information in coral monitoring, interpreting such images remains challenging due to the need for domain expertise. Visual Question Answering (VQA), powered by Large Vision-Language Models (LVLMs), has great potential in user-friendly interaction with coral reef images. However, applying VQA to coral imagery demands a dedicated dataset that addresses two key challenges: domain-specific annotations and multidimensional questions. In this work, we introduce CoralVQA, the first large-scale VQA dataset for coral reef analysis. It contains 12,805 real-world coral images from 67 coral genera collected from 3 oceans, along with 277,653 question-answer pairs that comprehensively assess ecological and health-related conditions. To construct this dataset, we develop a semi-automatic data construction pipeline in collaboration with marine biologists to ensure both scalability and professional-grade data quality. CoralVQA presents novel challenges and provides a comprehensive benchmark for studying vision-language reasoning in the context of coral reef images. By evaluating several state-of-the-art LVLMs, we reveal key limitations and opportunities. These insights form a foundation for future LVLM development, with a particular emphasis on supporting coral conservation efforts.

Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short query string. Previous approaches to this task have focused exclusively on abstracts, embedding them into dense vectors as surrogates for full documents and calculating similarity between them. Yet, abstracts offer only sparse and high-level summaries, and such methods primarily optimize one-to-one similarity, overlooking the dynamic relations that emerge among relevant papers during the retrieval process. To address this, we propose Chain of Retrieval(COR), a novel iterative framework for full-paper retrieval. Specifically, CoR decomposes each query paper into multiple aspect-specific views, matches them against segmented candidate papers, and iteratively expands the search by promoting top-ranked results as new queries, thereby forming a tree-structured retrieval process. The resulting retrieval tree is then aggregated in a post-order manner: descendants are first combined at the query level, then recursively merged with their parent nodes, to capture hierarchical relations across iterations. To validate this, we present SCIFULLBENCH, a large-scale benchmark providing both complete and segmented contexts of full papers for queries and candidates, and results show that CoR significantly outperforms existing retrieval baselines. Our code and dataset is available at https://github.com/psw0021/Chain-of-Retrieval.git.

While Knowledge Editing (KE) has been widely explored in English, its behavior in morphologically rich languages like Arabic remains underexamined. In this work, we present the first study of Arabic KE. We evaluate four methods (ROME, MEMIT, ICE, and LTE) on Arabic translations of the ZsRE and Counterfact benchmarks, analyzing both multilingual and cross-lingual settings. Our experiments on Llama-2-7B-chat show that parameter-based methods struggle with cross-lingual generalization, while instruction-tuned methods perform more robustly. We extend Learning-To-Edit (LTE) to a multilingual setting and show that joint Arabic-English training improves both editability and transfer. We release Arabic KE benchmarks and multilingual training for LTE data to support future research.

Early-stage engineering design involves complex, iterative reasoning, yet existing large language model (LLM) workflows struggle to maintain task continuity and generate executable models. We evaluate whether a structured multi-agent system (MAS) can more effectively manage requirements extraction, functional decomposition, and simulator code generation than a simpler two-agent system (2AS). The target application is a solar-powered water filtration system as described in a cahier des charges. We introduce the Design-State Graph (DSG), a JSON-serializable representation that bundles requirements, physical embodiments, and Python-based physics models into graph nodes. A nine-role MAS iteratively builds and refines the DSG, while the 2AS collapses the process to a Generator-Reflector loop. Both systems run a total of 60 experiments (2 LLMs - Llama 3.3 70B vs reasoning-distilled DeepSeek R1 70B x 2 agent configurations x 3 temperatures x 5 seeds). We report a JSON validity, requirement coverage, embodiment presence, code compatibility, workflow completion, runtime, and graph size. Across all runs, both MAS and 2AS maintained perfect JSON integrity and embodiment tagging. Requirement coverage remained minimal (less than 20%). Code compatibility peaked at 100% under specific 2AS settings but averaged below 50% for MAS. Only the reasoning-distilled model reliably flagged workflow completion. Powered by DeepSeek R1 70B, the MAS generated more granular DSGs (average 5-6 nodes) whereas 2AS mode-collapsed. Structured multi-agent orchestration enhanced design detail. Reasoning-distilled LLM improved completion rates, yet low requirements and fidelity gaps in coding persisted.

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the risks of privacy violations in the development and deployment of AI systems in high-stakes domains. Realizing this potential, however, requires principled consistent evaluations of synthetic data across multiple dimensions: its utility in downstream systems, the fairness of these systems, the risk of privacy leakage, general distributional differences from the source text, and qualitative feedback from domain experts. SynthTextEval allows users to conduct evaluations along all of these dimensions over synthetic data that they upload or generate using the toolkit's generation module. While our toolkit can be run over any data, we highlight its functionality and effectiveness over datasets from two high-stakes domains: healthcare and law. By consolidating and standardizing evaluation metrics, we aim to improve the viability of synthetic text, and in-turn, privacy-preservation in AI development.

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the reasoning trace, and (ii) compute is most effective when reasoning is systematic and incremental, forming structured chains of thought (CoTs) akin to human problem-solving. To study these factors in isolation, we introduce a controlled setting based on shortest-path tasks in layered graphs. We train decoder-only transformers on question-trace-answer triples using a custom tokenizer, comparing models trained on optimal bottom-up dynamic programming traces with those trained on longer, valid traces involving backtracking. Surprisingly, with the same training-token budget, models trained on inefficient traces generalize better to unseen graphs. This benefit is not due to length alone-injecting arbitrary redundancy into reasoning traces fails to help and can even hurt performance. Instead, we find that generalization correlates with the model's confidence in next-token prediction, suggesting that long, coherent, and locally incremental traces make the training signal easier to optimize.

We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of language models (LLMs) without fine-tuning model parameters. While prompt-based adaptation techniques have demonstrated the effectiveness of lightweight adaptation methods for LLMs, they typically initialize a trainable prompt or prefix with irrelevant tokens for the task at hand. In contrast, Context Tuning initializes the trainable prompt or prefix with task-specific demonstration examples, leveraging the model's inherent In-Context Learning (ICL) ability to extract relevant information for improved few-shot learning performance. Extensive evaluations on benchmarks such as CrossFit, UnifiedQA, MMLU, BIG-Bench Hard, and ARC demonstrate that Context Tuning outperforms traditional prompt-based adaptation methods and achieves competitive accuracy to Test-Time Training with significantly higher training efficiency.

Instruction Fine-Tuning (IFT) is crucial for aligning large language models (LLMs) with human preferences, and selecting a small yet representative subset from massive data significantly facilitates IFT in terms of both efficiency and effectiveness. Nevertheless, existing approaches suffer from two limitations: the use of simple heuristics restricts data diversity, while the singleton data quality evaluation accounts for inconsistent criteria between independent samples. To address the issues, we present TACOS, an innovative method that integrates Open Tagging and Comparative Scoring for IFT data selection. To capture data diversity, we leverage LLMs to assign open-domain tags to human queries, followed by a normalization stage to denoise the open tags and enable efficient clustering. Additionally, we suggest a comparative scoring method that allows the relative quality evaluation of samples within a cluster, avoiding inconsistent criteria seen in singleton-based evaluations. Extensive experiments across diverse datasets and LLM architectures demonstrate that TACOS outperforms existing approaches by a large margin. Notably, it achieves superior instruction-following performance on MT-Bench and ranks 1st among LLaMA2-7B-Based models on AlpacaEval 2.0, illustrating its efficacy for IFT data selection.

Moral self-correction has emerged as a promising approach for aligning the output of Large Language Models (LLMs) with human moral values. However, moral self-correction techniques are subject to two primary paradoxes. First, despite empirical and theoretical evidence to support the effectiveness of self-correction, this LLM capability only operates at a superficial level. Second, while LLMs possess the capability of self-diagnosing immoral aspects of their output, they struggle to identify the cause of this moral inconsistency during their self-correction process. To better understand and address these paradoxes, we analyze the discourse constructions in fine-tuning corpora designed to enhance moral self-correction, uncovering the existence of the heuristics underlying effective constructions. We demonstrate that moral self-correction relies on discourse constructions that reflect heuristic shortcuts, and that the presence of these heuristic shortcuts during self-correction leads to inconsistency when attempting to enhance both self-correction and self-diagnosis capabilities jointly. Based on our findings, we propose a solution to improve moral self-correction by leveraging the heuristics of curated datasets. We also highlight the generalization challenges of this capability, particularly in terms of learning from situated context and model scales.

The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection methods often struggle with generalization and capturing subtle temporal inconsistencies. We propose ReStraV(Representation Straightening Video), a novel approach to distinguish natural from AI-generated videos. Inspired by the "perceptual straightening" hypothesis -- which suggests real-world video trajectories become more straight in neural representation domain -- we analyze deviations from this expected geometric property. Using a pre-trained self-supervised vision transformer (DINOv2), we quantify the temporal curvature and stepwise distance in the model's representation domain. We aggregate statistics of these measures for each video and train a classifier. Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos. A lightweight classifier achieves state-of-the-art detection performance (e.g., 97.17% accuracy and 98.63% AUROC on the VidProM benchmark), substantially outperforming existing image- and video-based methods. ReStraV is computationally efficient, it is offering a low-cost and effective detection solution. This work provides new insights into using neural representation geometry for AI-generated video detection.