SEA-BED: Southeast Asia Embedding Benchmark

Sentence embeddings are essential for NLP tasks such as semantic search, re-ranking, and textual similarity. Although multilingual benchmarks like MMTEB broaden coverage, Southeast Asia (SEA) datasets are scarce and often machine-translated, missing native linguistic properties. With nearly 700 million speakers, the SEA region lacks a region-specific embedding benchmark. We introduce SEA-BED, the first large-scale SEA embedding benchmark with 169 datasets across 9 tasks and 10 languages, where 71% are formulated by humans, not machine generation or translation. We address three research questions: (1) which SEA languages and tasks are challenging, (2) whether SEA languages show unique performance gaps globally, and (3) how human vs. machine translations affect evaluation. We evaluate 17 embedding models across six studies, analyzing task and language challenges, cross-benchmark comparisons, and translation trade-offs. Results show sharp ranking shifts, inconsistent model performance among SEA languages, and the importance of human-curated datasets for low-resource languages like Burmese.

Understanding Refusal in Language Models with Sparse Autoencoders

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify latent features that causally mediate refusal behaviors. We apply our method to two open-source chat models and intervene on refusal-related features to assess their influence on generation, validating their behavioral impact across multiple harmful datasets. This enables a fine-grained inspection of how refusal manifests at the activation level and addresses key research questions such as investigating upstream-downstream latent relationship and understanding the mechanisms of adversarial jailbreaking techniques. We also establish the usefulness of refusal features in enhancing generalization for linear probes to out-of-distribution adversarial samples in classification tasks. We open source our code in https://github.com/wj210/refusal_sae.

Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation

Counterfactual reasoning typically involves considering alternatives to actual events. While often applied to understand past events, a distinct form-forward counterfactual reasoning-focuses on anticipating plausible future developments. This type of reasoning is invaluable in dynamic financial markets, where anticipating market developments can powerfully unveil potential risks and opportunities for stakeholders, guiding their decision-making. However, performing this at scale is challenging due to the cognitive demands involved, underscoring the need for automated solutions. Large Language Models (LLMs) offer promise, but remain unexplored for this application. To address this gap, we introduce a novel benchmark, Fin-Force-FINancial FORward Counterfactual Evaluation. By curating financial news headlines and providing structured evaluation, Fin-Force supports LLM based forward counterfactual generation. This paves the way for scalable and automated solutions for exploring and anticipating future market developments, thereby providing structured insights for decision-making. Through experiments on Fin-Force, we evaluate state-of-the-art LLMs and counterfactual generation methods, analyzing their limitations and proposing insights for future research.

Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages

Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements through specialized models like IndicXlit, recent developments in large language models suggest a potential for general-purpose models to excel at this task without explicit task-specific training. The current work systematically evaluates the performance of prominent LLMs, including GPT-4o, GPT-4.5, GPT-4.1, Gemma-3-27B-it, and Mistral-Large against IndicXlit, a state-of-the-art transliteration model, across ten major Indian languages. Experiments utilized standard benchmarks, including Dakshina and Aksharantar datasets, with performance assessed via Top-1 Accuracy and Character Error Rate. Our findings reveal that while GPT family models generally outperform other LLMs and IndicXlit for most instances. Additionally, fine-tuning GPT-4o improves performance on specific languages notably. An extensive error analysis and robustness testing under noisy conditions further elucidate strengths of LLMs compared to specialized models, highlighting the efficacy of foundational models for a wide spectrum of specialized applications with minimal overhead.

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

Large language models (LLMs) have shown promise in automating scientific hypothesis generation, yet existing approaches primarily yield coarse-grained hypotheses lacking critical methodological and experimental details. We introduce and formally define the novel task of fine-grained scientific hypothesis discovery, which entails generating detailed, experimentally actionable hypotheses from coarse initial research directions. We frame this as a combinatorial optimization problem and investigate the upper limits of LLMs' capacity to solve it when maximally leveraged. Specifically, we explore four foundational questions: (1) how to best harness an LLM's internal heuristics to formulate the fine-grained hypothesis it itself would judge as the most promising among all the possible hypotheses it might generate, based on its own internal scoring-thus defining a latent reward landscape over the hypothesis space; (2) whether such LLM-judged better hypotheses exhibit stronger alignment with ground-truth hypotheses; (3) whether shaping the reward landscape using an ensemble of diverse LLMs of similar capacity yields better outcomes than defining it with repeated instances of the strongest LLM among them; and (4) whether an ensemble of identical LLMs provides a more reliable reward landscape than a single LLM. To address these questions, we propose a hierarchical search method that incrementally proposes and integrates details into the hypothesis, progressing from general concepts to specific experimental configurations. We show that this hierarchical process smooths the reward landscape and enables more effective optimization. Empirical evaluations on a new benchmark of expert-annotated fine-grained hypotheses from recent chemistry literature show that our method consistently outperforms strong baselines.

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads

Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadvertently learn spurious associations between target variables and confounding factors. To address this, we introduce \textsc{Locate-Then-Correct} (LTC), a contrastive framework that identifies spurious attention heads in Vision Transformers via mechanistic insights and mitigates them through targeted ablation. Furthermore, LTC identifies salient, task-relevant attention heads, enabling the integration of discriminative features through orthogonal projection to improve classification performance. We evaluate LTC on benchmarks with inherent background and gender biases, achieving over a $>50\%$ gain in worst-group accuracy compared to non-training post-hoc baselines. Additionally, we visualize the representation of selected heads and find that the presented interpretation corroborates our contrastive mechanism for identifying both spurious and salient attention heads. Code available at https://github.com/wj210/CLIP_LTC.

MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

Hypothesis ranking is a crucial component of automated scientific discovery, particularly in natural sciences where wet-lab experiments are costly and throughput-limited. Existing approaches focus on pre-experiment ranking, relying solely on large language model's internal reasoning without incorporating empirical outcomes from experiments. We introduce the task of experiment-guided ranking, which aims to prioritize candidate hypotheses based on the results of previously tested ones. However, developing such strategies is challenging due to the impracticality of repeatedly conducting real experiments in natural science domains. To address this, we propose a simulator grounded in three domain-informed assumptions, modeling hypothesis performance as a function of similarity to a known ground truth hypothesis, perturbed by noise. We curate a dataset of 124 chemistry hypotheses with experimentally reported outcomes to validate the simulator. Building on this simulator, we develop a pseudo experiment-guided ranking method that clusters hypotheses by shared functional characteristics and prioritizes candidates based on insights derived from simulated experimental feedback. Experiments show that our method outperforms pre-experiment baselines and strong ablations.

Neural Brain: A Neuroscience-inspired Framework for Embodied Agents

The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments. Despite advancements in pattern recognition and symbolic reasoning, current AI systems, such as large language models, remain disembodied, unable to physically engage with the world. This limitation has driven the rise of embodied AI, where autonomous agents, such as humanoid robots, must navigate and manipulate unstructured environments with human-like adaptability. At the core of this challenge lies the concept of Neural Brain, a central intelligence system designed to drive embodied agents with human-like adaptability. A Neural Brain must seamlessly integrate multimodal sensing and perception with cognitive capabilities. Achieving this also requires an adaptive memory system and energy-efficient hardware-software co-design, enabling real-time action in dynamic environments. This paper introduces a unified framework for the Neural Brain of embodied agents, addressing two fundamental challenges: (1) defining the core components of Neural Brain and (2) bridging the gap between static AI models and the dynamic adaptability required for real-world deployment. To this end, we propose a biologically inspired architecture that integrates multimodal active sensing, perception-cognition-action function, neuroplasticity-based memory storage and updating, and neuromorphic hardware/software optimization. Furthermore, we also review the latest research on embodied agents across these four aspects and analyze the gap between current AI systems and human intelligence. By synthesizing insights from neuroscience, we outline a roadmap towards the development of generalizable, autonomous agents capable of human-level intelligence in real-world scenarios.

ClimaEmpact: Domain-Aligned Small Language Models and Datasets for Extreme Weather Analytics

Accurate assessments of extreme weather events are vital for research and policy, yet localized and granular data remain scarce in many parts of the world. This data gap limits our ability to analyze potential outcomes and implications of extreme weather events, hindering effective decision-making. Large Language Models (LLMs) can process vast amounts of unstructured text data, extract meaningful insights, and generate detailed assessments by synthesizing information from multiple sources. Furthermore, LLMs can seamlessly transfer their general language understanding to smaller models, enabling these models to retain key knowledge while being fine-tuned for specific tasks. In this paper, we propose Extreme Weather Reasoning-Aware Alignment (EWRA), a method that enhances small language models (SLMs) by incorporating structured reasoning paths derived from LLMs, and ExtremeWeatherNews, a large dataset of extreme weather event-related news articles. EWRA and ExtremeWeatherNews together form the overall framework, ClimaEmpact, that focuses on addressing three critical extreme-weather tasks: categorization of tangible vulnerabilities/impacts, topic labeling, and emotion analysis. By aligning SLMs with advanced reasoning strategies on ExtremeWeatherNews (and its derived dataset ExtremeAlign used specifically for SLM alignment), EWRA improves the SLMs' ability to generate well-grounded and domain-specific responses for extreme weather analytics. Our results show that the approach proposed guides SLMs to output domain-aligned responses, surpassing the performance of task-specific models and offering enhanced real-world applicability for extreme weather analytics.

Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis

Multimodal aspect-based sentiment classification (MASC) is an emerging task due to an increase in user-generated multimodal content on social platforms, aimed at predicting sentiment polarity toward specific aspect targets (i.e., entities or attributes explicitly mentioned in text-image pairs). Despite extensive efforts and significant achievements in existing MASC, substantial gaps remain in understanding fine-grained visual content and the cognitive rationales derived from semantic content and impressions (cognitive interpretations of emotions evoked by image content). In this study, we present Chimera: a cognitive and aesthetic sentiment causality understanding framework to derive fine-grained holistic features of aspects and infer the fundamental drivers of sentiment expression from both semantic perspectives and affective-cognitive resonance (the synergistic effect between emotional responses and cognitive interpretations). Specifically, this framework first incorporates visual patch features for patch-word alignment. Meanwhile, it extracts coarse-grained visual features (e.g., overall image representation) and fine-grained visual regions (e.g., aspect-related regions) and translates them into corresponding textual descriptions (e.g., facial, aesthetic). Finally, we leverage the sentimental causes and impressions generated by a large language model (LLM) to enhance the model's awareness of sentimental cues evoked by semantic content and affective-cognitive resonance. Experimental results on standard MASC datasets demonstrate the effectiveness of the proposed model, which also exhibits greater flexibility to MASC compared to LLMs such as GPT-4o. We have publicly released the complete implementation and dataset at https://github.com/Xillv/Chimera