Automated counter-narratives (CN) offer a promising strategy for mitigating online hate speech, yet concerns about their affective tone, accessibility, and ethical risks remain. We propose a framework for evaluating Large Language Model (LLM)-generated CNs across four dimensions: persona framing, verbosity and readability, affective tone, and ethical robustness. Using GPT-4o-Mini, Cohere's CommandR-7B, and Meta's LLaMA 3.1-70B, we assess three prompting strategies on the MT-Conan and HatEval datasets. Our findings reveal that LLM-generated CNs are often verbose and adapted for people with college-level literacy, limiting their accessibility. While emotionally guided prompts yield more empathetic and readable responses, there remain concerns surrounding safety and effectiveness.
Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the generated documents, which often requires complex prompt strategies and the integration of advanced dense retrieval techniques. This can be both costly and computationally intensive. To mitigate these limitations, we explore the use of zero-shot LLM-based query expansion to improve sparse retrieval, particularly for learned sparse retrievers. We introduce a novel fusion ranking framework, Exp4Fuse, which enhances the performance of sparse retrievers through an indirect application of zero-shot LLM-based query expansion. Exp4Fuse operates by simultaneously considering two retrieval routes-one based on the original query and the other on the LLM-augmented query. It then generates two ranked lists using a sparse retriever and fuses them using a modified reciprocal rank fusion method. We conduct extensive evaluations of Exp4Fuse against leading LLM-based query expansion methods and advanced retrieval techniques on three MS MARCO-related datasets and seven low-resource datasets. Experimental results reveal that Exp4Fuse not only surpasses existing LLM-based query expansion methods in enhancing sparse retrievers but also, when combined with advanced sparse retrievers, achieves SOTA results on several benchmarks. This highlights the superior performance and effectiveness of Exp4Fuse in improving query expansion for sparse retrieval.
Computational Fluid Dynamics (CFD) is essential for scientific and engineering advancements but is limited by operational complexity and the need for extensive expertise. This paper presents ChatCFD, a large language model-driven pipeline that automates CFD workflows within the OpenFOAM framework. It enables users to configure and execute complex simulations from natural language prompts or published literature with minimal expertise. The innovation is its structured approach to database construction, configuration validation, and error reflection, integrating CFD and OpenFOAM knowledge with general language models to improve accuracy and adaptability. Validation shows ChatCFD can autonomously reproduce published CFD results, handling complex, unseen configurations beyond basic examples, a task challenging for general language models.
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance. Through rigorous data preprocessing, reward design, and tailored training strategies, our method leverages simple rule-based outcome rewards to outperform SFT across multiple benchmarks. Unified training across diverse tasks enables Reasoning-Table to emerge as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0% on table reasoning benchmarks. The approach also achieves excellent performance on text-to-SQL tasks, reaching 68.3% performance on the BIRD dev dataset with a 7B model. Further experiments demonstrate that Reasoning-Table enhances the model's generalization capabilities and robustness.
Periodic or quasi-periodic phenomena reveal intrinsic characteristics in various natural processes, such as weather patterns, movement behaviors, traffic flows, and biological signals. Given that these phenomena span multiple modalities, the capabilities of Multimodal Large Language Models (MLLMs) offer promising potential to effectively capture and understand their complex nature. However, current MLLMs struggle with periodic tasks due to limitations in: 1) lack of temporal modelling and 2) conflict between short and long periods. This paper introduces Period-LLM, a multimodal large language model designed to enhance the performance of periodic tasks across various modalities, and constructs a benchmark of various difficulty for evaluating the cross-modal periodic capabilities of large models. Specially, We adopt an "Easy to Hard Generalization" paradigm, starting with relatively simple text-based tasks and progressing to more complex visual and multimodal tasks, ensuring that the model gradually builds robust periodic reasoning capabilities. Additionally, we propose a "Resisting Logical Oblivion" optimization strategy to maintain periodic reasoning abilities during semantic alignment. Extensive experiments demonstrate the superiority of the proposed Period-LLM over existing MLLMs in periodic tasks. The code is available at https://github.com/keke-nice/Period-LLM.
Extensively evaluating the capabilities of (large) language models is difficult. Rapid development of state-of-the-art models induce benchmark saturation, while creating more challenging datasets is labor-intensive. Inspired by the recent developments in mechanistic interpretability, we introduce circuit stability as a new way to assess model performance. Circuit stability refers to a model's ability to apply a consistent reasoning process-its circuit-across various inputs. We mathematically formalize circuit stability and circuit equivalence. Then, through three case studies, we empirically show that circuit stability and the lack thereof can characterize and predict different aspects of generalization. Our proposed methods offer a step towards rigorously relating the generality of models to their interpretability.
Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploited for malicious purposes. Although safety alignment datasets have been introduced to mitigate such risks through supervised fine-tuning (SFT), these datasets often lack comprehensive risk coverage. Most existing datasets focus primarily on lexical diversity while neglecting other critical dimensions. To address this limitation, we propose a novel analysis framework to systematically measure the risk coverage of alignment datasets across three essential dimensions: Lexical Diversity, Malicious Intent, and Jailbreak Tactics. We further introduce TRIDENT, an automated pipeline that leverages persona-based, zero-shot LLM generation to produce diverse and comprehensive instructions spanning these dimensions. Each harmful instruction is paired with an ethically aligned response, resulting in two datasets: TRIDENT-Core, comprising 26,311 examples, and TRIDENT-Edge, with 18,773 examples. Fine-tuning Llama 3.1-8B on TRIDENT-Edge demonstrates substantial improvements, achieving an average 14.29% reduction in Harm Score, and a 20% decrease in Attack Success Rate compared to the best-performing baseline model fine-tuned on the WildBreak dataset.
Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank decomposition methods offer a promising path for structural compression, they often suffer from accuracy degradation, expensive calibration procedures, and result in inefficient model architectures that hinder real-world inference speedups. In this paper, we propose FLAT-LLM, a fast and accurate, training-free structural compression method based on fine-grained low-rank transformations in the activation space. Specifically, we reduce the hidden dimension by transforming the weights using truncated eigenvectors computed via head-wise Principal Component Analysis (PCA), and employ an importance-based metric to adaptively allocate ranks across decoders. FLAT-LLM achieves efficient and effective weight compression without recovery fine-tuning, which could complete the calibration within a few minutes. Evaluated across 4 models and 11 datasets, FLAT-LLM outperforms structural pruning baselines in generalization and downstream performance, while delivering inference speedups over decomposition-based methods.
Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we introduce a flexible and efficient data mixing framework, Chameleon, that employs leverage scores to quantify domain importance within a learned embedding space. We first construct a domain affinity matrix over domain embeddings. The induced leverage scores determine a mixture that upweights domains sharing common representations in embedding space. This formulation allows direct transfer to new data by computing the new domain embeddings. In experiments, we demonstrate improvements over three key scenarios: (i) our computed weights improve performance on pretraining domains with a fraction of the compute of existing methods; (ii) Chameleon can adapt to data changes without proxy retraining, boosting few-shot reasoning accuracies when transferred to new data; (iii) our method enables efficient domain reweighting in finetuning, consistently improving test perplexity on all finetuning domains over uniform mixture. Our code is available at https://github.com/LIONS-EPFL/Chameleon.
Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models. Inference-Time Decomposition of Activations (ITDA) is a recently proposed variant of dictionary learning that takes the dictionary to be a set of data points from the activation distribution and reconstructs them with gradient pursuit. We apply Sparse Autoencoders (SAEs) and ITDA to a large text-to-image diffusion model, Flux 1, and consider the interpretability of embeddings of both by introducing a visual automated interpretation pipeline. We find that SAEs accurately reconstruct residual stream embeddings and beat MLP neurons on interpretability. We are able to use SAE features to steer image generation through activation addition. We find that ITDA has comparable interpretability to SAEs.
Classifying geospatial imagery remains a major bottleneck for applications such as disaster response and land-use monitoring-particularly in regions where annotated data is scarce or unavailable. Existing tools (e.g., RS-CLIP) that claim zero-shot classification capabilities for satellite imagery nonetheless rely on task-specific pretraining and adaptation to reach competitive performance. We introduce GeoVision Labeler (GVL), a strictly zero-shot classification framework: a vision Large Language Model (vLLM) generates rich, human-readable image descriptions, which are then mapped to user-defined classes by a conventional Large Language Model (LLM). This modular, and interpretable pipeline enables flexible image classification for a large range of use cases. We evaluated GVL across three benchmarks-SpaceNet v7, UC Merced, and RESISC45. It achieves up to 93.2% zero-shot accuracy on the binary Buildings vs. No Buildings task on SpaceNet v7. For complex multi-class classification tasks (UC Merced, RESISC45), we implemented a recursive LLM-driven clustering to form meta-classes at successive depths, followed by hierarchical classification-first resolving coarse groups, then finer distinctions-to deliver competitive zero-shot performance. GVL is open-sourced at https://github.com/microsoft/geo-vision-labeler to catalyze adoption in real-world geospatial workflows.
Originally, dropout was seen as a breakthrough regularization technique that reduced overfitting and improved performance in almost all applications of deep learning by reducing overfitting. Yet, single-epoch pretraining tasks common to modern LLMs yield minimal overfitting, leading to dropout not being used for large LLMs. Nevertheless, no thorough empirical investigation has been done on the role of dropout in LM pretraining. Through experiments in single-epoch pretraining of both masked (BERT) and autoregressive (Pythia 160M and 1.4B) LMs with varying levels of dropout, we find that downstream performance in language modeling, morpho-syntax (BLiMP), question answering (SQuAD), and natural-language inference (MNLI) improves when dropout is not applied during pretraining. We additionally find that the recently-introduced "early dropout" also degrades performance over applying no dropout at all. We further investigate the models' editability, and find that models trained without dropout are more successful in gradient-based model editing (MEND) and equivalent in representation-based model editing (ReFT). Therefore, we advocate to drop dropout during single-epoch pretraining.
Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling. Despite their effectiveness, these methods often follow a fast thinking paradigm emphasizing pattern extraction and direct value mapping, while overlooking explicit reasoning over temporal dynamics and contextual dependencies. Meanwhile, emerging slow-thinking LLMs (e.g., ChatGPT-o1, DeepSeek-R1) have demonstrated impressive multi-step reasoning capabilities across diverse domains, suggesting a new opportunity for reframing TSF as a structured reasoning task. This motivates a key question: can slow-thinking LLMs effectively reason over temporal patterns to support time series forecasting, even in zero-shot manner? To investigate this, in this paper, we propose TimeReasoner, an extensive empirical study that formulates TSF as a conditional reasoning task. We design a series of prompting strategies to elicit inference-time reasoning from pretrained slow-thinking LLMs and evaluate their performance across diverse TSF benchmarks. Our findings reveal that slow-thinking LLMs exhibit non-trivial zero-shot forecasting capabilities, especially in capturing high-level trends and contextual shifts. While preliminary, our study surfaces important insights into the reasoning behaviors of LLMs in temporal domains highlighting both their potential and limitations. We hope this work catalyzes further research into reasoning-based forecasting paradigms and paves the way toward more interpretable and generalizable TSF frameworks.
Faithfulness hallucinations are claims generated by a Large Language Model (LLM) not supported by contexts provided to the LLM. Lacking assessment standards, existing benchmarks focus on "factual statements" that rephrase source materials while overlooking "cognitive statements" that involve making inferences from the given context. Consequently, evaluating and detecting the hallucination of cognitive statements remains challenging. Inspired by how evidence is assessed in the legal domain, we design a rigorous framework to assess different levels of faithfulness of cognitive statements and introduce the CogniBench dataset where we reveal insightful statistics. To keep pace with rapidly evolving LLMs, we further develop an automatic annotation pipeline that scales easily across different models. This results in a large-scale CogniBench-L dataset, which facilitates training accurate detectors for both factual and cognitive hallucinations. We release our model and datasets at: https://github.com/FUTUREEEEEE/CogniBench
Neural speech codecs have revolutionized speech coding, achieving higher compression while preserving audio fidelity. Beyond compression, they have emerged as tokenization strategies, enabling language modeling on speech and driving paradigm shifts across various speech processing tasks. Despite these advancements, their robustness in noisy environments remains underexplored, raising concerns about their generalization to real-world scenarios. In this work, we systematically evaluate neural speech codecs under various noise conditions, revealing non-trivial differences in their robustness. We further examine their linearity properties, uncovering non-linear distortions which partly explain observed variations in robustness. Lastly, we analyze their frequency response to identify factors affecting audio fidelity. Our findings provide critical insights into codec behavior and future codec design, as well as emphasizing the importance of noise robustness for their real-world integration.
Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly being applied to decisions with procedural tasks, have not been systematically evaluated for their ability to perform data-flow reasoning. We introduce FABLE, an extensible benchmark designed to assess LLMs' understanding of data flow using structured, procedural text. FABLE adapts eight classical data-flow analyses from software engineering: reaching definitions, very busy expressions, available expressions, live variable analysis, interval analysis, type-state analysis, taint analysis, and concurrency analysis. These analyses are instantiated across three real-world domains: cooking recipes, travel routes, and automated plans. The benchmark includes 2,400 question-answer pairs, with 100 examples for each domain-analysis combination. We evaluate three types of LLMs: a reasoning-focused model (DeepSeek-R1 8B), a general-purpose model (LLaMA 3.1 8B), and a code-specific model (Granite Code 8B). Each model is tested using majority voting over five sampled completions per prompt. Results show that the reasoning model achieves higher accuracy, but at the cost of over 20 times slower inference compared to the other models. In contrast, the general-purpose and code-specific models perform close to random chance. FABLE provides the first diagnostic benchmark to systematically evaluate data-flow reasoning and offers insights for developing models with stronger procedural understanding.
Document-level context is crucial for handling discourse challenges in text-to-text document-level machine translation (MT). Despite the increased discourse challenges introduced by noise from automatic speech recognition (ASR), the integration of document-level context in speech translation (ST) remains insufficiently explored. In this paper, we develop DoCIA, an online framework that enhances ST performance by incorporating document-level context. DoCIA decomposes the ST pipeline into four stages. Document-level context is integrated into the ASR refinement, MT, and MT refinement stages through auxiliary LLM (large language model)-based modules. Furthermore, DoCIA leverages document-level information in a multi-level manner while minimizing computational overhead. Additionally, a simple yet effective determination mechanism is introduced to prevent hallucinations from excessive refinement, ensuring the reliability of the final results. Experimental results show that DoCIA significantly outperforms traditional ST baselines in both sentence and discourse metrics across four LLMs, demonstrating its effectiveness in improving ST performance.
Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks. Recent efforts have advanced PRMs from step-level to token-level granularity by integrating reward modeling into the training of generative models, with reward scores derived from token generation probabilities. However, the conflict between generative language modeling and reward modeling may introduce instability and lead to inaccurate credit assignments. To address this challenge, we revisit token-level reward assignment by decoupling reward modeling from language generation and derive a token-level reward model through the optimization of a discriminative policy, termed the Q-function Reward Model (Q-RM). We theoretically demonstrate that Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations. In our experiments, Q-RM consistently outperforms all baseline methods across various benchmarks. For example, when integrated into PPO/REINFORCE algorithms, Q-RM enhances the average Pass@1 score by 5.85/4.70 points on mathematical reasoning tasks compared to the ORM baseline, and by 4.56/5.73 points compared to the token-level PRM counterpart. Moreover, reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH. Code and data are available at https://github.com/homzer/Q-RM.
Recent advances in language modeling have underscored the role of preference feedback in enhancing model performance. This paper investigates the conditions under which preference feedback improves parameter estimation in classes of continuous parametric distributions. In our framework, the learner observes pairs of samples from an unknown distribution along with their relative preferences depending on the same unknown parameter. We show that preference-based M-estimators achieve a better asymptotic variance than sample-only M-estimators, further improved by deterministic preferences. Leveraging the hard constraints revealed by deterministic preferences, we propose an estimator achieving an estimation error scaling of $\mathcal{O}(1/n)$ -- a significant improvement over the $\Theta(1/\sqrt{n})$ rate attainable with samples alone. Next, we establish a lower bound that matches this accelerated rate; up to dimension and problem-dependent constants. While the assumptions underpinning our analysis are restrictive, they are satisfied by notable cases such as Gaussian or Laplace distributions for preferences based on the log-probability reward.
The proliferation of online news and the increasing spread of misinformation necessitate robust methods for automatic data analysis. Narrative classification is emerging as a important task, since identifying what is being said online is critical for fact-checkers, policy markers and other professionals working on information studies. This paper presents our approach to SemEval 2025 Task 10 Subtask 2, which aims to classify news articles into a pre-defined two-level taxonomy of main narratives and sub-narratives across multiple languages. We propose Hierarchical Three-Step Prompting (H3Prompt) for multilingual narrative classification. Our methodology follows a three-step Large Language Model (LLM) prompting strategy, where the model first categorises an article into one of two domains (Ukraine-Russia War or Climate Change), then identifies the most relevant main narratives, and finally assigns sub-narratives. Our approach secured the top position on the English test set among 28 competing teams worldwide. The code is available at https://github.com/GateNLP/H3Prompt.