Anomaly detection (AD) is an important machine learning task with applications in fraud detection, content moderation, and user behavior analysis. However, AD is relatively understudied in a natural language processing (NLP) context, limiting its effectiveness in detecting harmful content, phishing attempts, and spam reviews. We introduce NLP-ADBench, the most comprehensive NLP anomaly detection (NLP-AD) benchmark to date, which includes eight curated datasets and 19 state-of-the-art algorithms. These span 3 end-to-end methods and 16 two-step approaches that adapt classical, non-AD methods to language embeddings from BERT and OpenAI. Our empirical results show that no single model dominates across all datasets, indicating a need for automated model selection. Moreover, two-step methods with transformer-based embeddings consistently outperform specialized end-to-end approaches, with OpenAI embeddings outperforming those of BERT. We release NLP-ADBench at https://github.com/USC-FORTIS/NLP-ADBench, providing a unified framework for NLP-AD and supporting future investigations.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Oversensitivity occurs when language models defensively reject prompts that are actually benign. This behavior not only disrupts user interactions but also obscures the boundary between harmful and harmless content. Existing benchmarks rely on static datasets that degrade over time as models evolve, leading to data contamination and diminished evaluative power. To address this, we develop a framework that dynamically generates model-specific challenging datasets, capturing emerging defensive patterns and aligning with each model’s unique behavior. Building on this approach, we construct OverBench, a benchmark that aggregates these datasets across diverse LLM families, encompassing 450,000 samples from 25 models. OverBench provides a dynamic and evolving perspective on oversensitivity, allowing for continuous monitoring of defensive triggers as models advance, highlighting vulnerabilities that static datasets overlook.
Accurate analysis of pathological images is essential for automated tumor diagnosis but remains challenging due to high structural similarity and subtle morphological variations in tissue images. Current vision-language (VL) models often struggle to capture the complex reasoning required for interpreting structured pathological reports. To address these limitations, we propose PathoHR-Bench, a novel benchmark designed to evaluate VL models’ abilities in hierarchical semantic understanding and compositional reasoning within the pathology domain. Results of this benchmark reveal that existing VL models fail to effectively model intricate cross-modal relationships, hence limiting their applicability in clinical setting. To overcome this, we further introduce a pathology-specific VL training scheme that generates enhanced and perturbed samples for multimodal contrastive learning. Experimental evaluations demonstrate that our approach achieves state-of-the-art performance on PathoHR-Bench and six additional pathology datasets, highlighting its effectiveness in fine-grained pathology representation.
Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating strong capabilities in tasks such as text generation, summarization, and reasoning. Recently, their potential for automating precise text editing tasks across specialized domains, such as programming code, LaTeX, and structured database languages, has gained attention. However, current state-of-the-art LLMs still struggle with executing precise, instruction-driven edits, particularly when structural accuracy and strict adherence to domain conventions are required.To address these challenges, we introduce InstrEditBench, an automated benchmark dataset comprising over 30,000 structured editing tasks spanning diverse domains, including Wikipedia articles, LaTeX documents, source code, and database languages. Using this benchmark, we develop FineEdit, a specialized editing model explicitly trained for accurate, context-aware text modifications. Experimental evaluations demonstrate that FineEdit outperforms state-of-the-art models, achieving improvements of approximately 10% over Gemini models on single-turn edits, up to 30% over Llama-3.2-3B, and exceeding Mistral-7B-OpenOrca performance by over 40% on direct editing tasks. FineEdit also effectively generalizes to realistic multi-turn editing scenarios, highlighting its practical applicability. To facilitate further research and reproducibility, we release FineEdit at https://github.com/StuRinDQB/FineEdit and https://huggingface.co/datasets/YimingZeng/FineEdit_bench.
Large language models (LLMs) are trained using massive datasets.However, these datasets often contain undesirable content, e.g., harmful texts, personal information, and copyrighted material.To address this, machine unlearning aims to remove information from trained models.Recent work has shown that soft token attacks () can successfully extract unlearned information from LLMs.In this work, we show that s can be an inadequate tool for auditing unlearning.Using common unlearning benchmarks, i.e., Who Is Harry Potter? and TOFU, we demonstrate that, in a strong auditor setting, such attacks can elicit any information from the LLM, regardless of (1) the deployed unlearning algorithm, and (2) whether the queried content was originally present in the training corpus.Also, we show that with just a few soft tokens (1-10) can elicit random strings over 400-characters long.Thus showing that s must be used carefully to effectively audit unlearning.Example code can be found at https://github.com/IntelLabs/LLMart/tree/main/examples/unlearning
While Ukrainian NLP has seen progress in many texts processing tasks, emotion classification remains an underexplored area with no publicly available benchmark to date. In this work, we introduce **EmoBench-UA**, the first annotated dataset for emotion detection in Ukrainian texts. Our annotation schema is adapted from the previous English-centric works on emotion detection (Mohammad et al., 2018; Mohammad, 2022) guidelines. The dataset was created through crowdsourcing using the Toloka.ai platform ensuring high-quality of the annotation process. Then, we evaluate a range of approaches on the collected dataset, starting from linguistic-based baselines, synthetic data translated from English, to large language models (LLMs). Our findings highlight the challenges of emotion classification in non-mainstream languages like Ukrainian and emphasize the need for further development of Ukrainian-specific models and training resources.
The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filtering towards image-text interleaved document data is under-explored. We propose to train an efficient MLLM as a Unified Mulitmodal Data Quality Classifier to Filter both high-quality image-text caption and interleaved data (UniFilter). To address the challenge of collecting diverse labeled multimodal data, we introduce a semi-synthetic approach that leverages readily available raw images and generates corresponding text across four quality levels. This method enables efficient creation of sample-score pairs for both caption and interleaved document data to train UniFilter. We apply UniFilter to curate high-quality caption data from DataComp caption dataset and interleaved data from the OBELICS image-text interleaved dataset. MLLMs pre-trained on the filtered data demonstrate significantly enhanced capabilities compared to those trained on baseline-filtered data, achieving stronger zero-shot reasoning and in-context learning capabilities. After visual supervised fine-tuning, these UniFilter-induced MLLMs achieve stronger performance on various benchmarks, highlighting the downstream benefits of high-quality multimodal pre-training.
Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models
PDF ↗High-quality data resources play a crucial role in learning large language models (LLMs), particularly for low-resource languages like Cantonese. Despite having more than 85 million native speakers, Cantonese is still considered a low-resource language in the field of natural language processing (NLP) due to factors such as the dominance of Mandarin, lack of cohesion within the Cantonese-speaking community, diversity in character encoding and input methods, and the tendency of overseas Cantonese speakers to prefer using English. In addition, rich colloquial vocabulary of Cantonese, English loanwords, and code-switching characteristics add to the complexity of corpus collection and processing. To address these challenges, we collect Cantonese texts from a variety of sources, including open source corpora, Hong Kong-specific forums, Wikipedia, and Common Crawl data. We conduct rigorous data processing through language filtering, quality filtering, content filtering, and de-duplication steps, successfully constructing a high-quality Cantonese corpus of over 2 billion tokens for training large language models. We further refined the model through supervised fine-tuning (SFT) on curated Cantonese tasks, enhancing its ability to handle specific applications. Upon completion of the training, the model achieves state-of-the-art (SOTA) performance on four Cantonese benchmarks. After training on our dataset, the model also exhibits improved performance on other mainstream language tasks.
Memory-enhanced Large Language Model for Cross-lingual Dependency Parsing via Deep Hierarchical Syntax Understanding
PDF ↗Large language models (LLMs) demonstrate remarkable text generation and syntax parsing capabilities in high-resource languages. However, their performance notably declines in low-resource languages due to memory forgetting stemming from semantic interference across languages. To address this issue, we propose a novel deep hierarchical syntax understanding approach to improve the cross-lingual semantic memory capability of LLMs. First, we design a multi-task joint fine-tuning strategy to implicitly align linguistic knowledge between source and target languages in LLMs, which is leveraged to initially parse the target text. Second, we automatically construct the multilingual dependency label banks based on the statistical structure information from the Universal Dependencies (UD) data. Third, we obtain each label’s memory strength via in-depth analysis of the initial parsing tree and its dependency label bank. Finally, memory strength is further exploited to guide LLMs to learn the linguistic commonalities from multilingual dependency label banks, thus activating the memory ability of weak labels. Experimental results on four benchmark datasets show that our method can dramatically improve the parsing accuracy of all baseline models, leading to new state-of-the-art results. Further analysis reveals that our approach can effectively enhance the weak syntactic label memory cognition of LLMs by combining the advantages of both implicit multi-task fine-tuning and explicit label bank guiding. Our code and dependency label banks are released at https://github.com/Flamelunar/memory_dep.
CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP’s language supervision or its much larger training data. To disentangle these factors, we pre-train CLIP and DINO under controlled settings—using the same architecture, dataset, and training configuration—achieving similar ImageNet accuracy. Embedding analysis shows that CLIP captures high-level semantics (e.g., object categories, text), while DINO is more responsive to low-level features like colors and styles. When integrated into VLMs and evaluated on 20 VQA benchmarks, CLIP excels at text-intensive tasks, while DINO slightly outperforms on vision-centric ones. Variants of language supervision (e.g., sigmoid loss, pre-trained language encoders) yield limited gains. Our findings provide scientific insights into vision encoder design and its impact on VLM performance.
In legal practice, judges apply the trichotomous dogmatics of criminal law, sequentially assessingthe elements of the offense, unlawfulness, and culpability to determine whether an individual’s conduct constitutes a crime. Although current legal large language models (LLMs) show promising accuracy in judgment prediction, they lack trichotomous reasoning capabilities due to the absence of an appropriate benchmark dataset, preventing them from predicting innocent outcomes. As a result, every input is automatically assigned a charge, limiting their practical utility in legal contexts. To bridge this gap, we introduce LJPIV, the first benchmark dataset for Legal Judgment Prediction with Innocent Verdicts. Adhering to the trichotomous dogmatics, we extend three widely-used legal datasets through LLM-based augmentation and manual verification. Our experiments with state-of-the-art legal LLMs and novel strategies that integrate trichotomous reasoning into zero-shot prompting and fine-tuning reveal: (1) current legal LLMs have significant room for improvement, with even the best models achieving an F1 score of less than 0.3 on LJPIV; and (2) our strategies notably enhance both in-domain and cross-domain judgment prediction accuracy, especially for cases resulting in an innocent verdict.
Step-by-step reasoning is widely used to enhance the reasoning ability of large language models (LLMs) in complex problems. Evaluating the quality of reasoning traces is crucial for understanding and improving LLM reasoning. However, existing evaluation practices are highly inconsistent, resulting in fragmented progress across evaluator design and benchmark development. To address this gap, this survey provides a comprehensive overview of step-by-step reasoning evaluation, proposing a taxonomy of evaluation criteria with four top-level categories (factuality, validity, coherence, and utility). Based on the taxonomy, we review different datasets, evaluator implementations, and recent findings, leading to promising directions for future research.
Critique ability, a meta-cognitive capability of humans, presents significant challenges for LLMs to improve. While utilizing human annotation can enhance critique ability effectively, most recent works primarily rely on supervised fine-tuning (SFT) using critiques generated by a single LLM like GPT-4, which is more scalable and cost-effective.However, such model-generated critiques often suffer from inherent flaws due to the complexity of critique. Consequently, fine-tuning LLMs on these flawed critiques not only limits performance but also propagates errors into the learned model.To address this issue, we propose MultiCritique, a unified framework that leverages multi-agent feedback to improve critique ability in both the supervised fine-tuning (SFT) and reinforcement learning (RL) stages.In the SFT stage, MultiCritique aggregates high-quality multi-agent critiques through a fine-grained meta-critique mechanism. In the RL stage, preference critiques are constructed and refined by validating their contributions to revisions, thereby enhancing robustness of RL in improving critique ability.Based on MultiCritique, we construct SFT and RL datasets. Extensive experimental results on two benchmarks highlight the key benefits of our dataset, including superior quality, enhanced data efficiency, strong generalization on unseen tasks, and improvements in the general capability of LLMs.Notably, our fine-tuned 7B model significantly surpasses advanced 7B-13B models, approaching advanced 70B LLMs and GPT-4.Resources have been publicly available.
What’s Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs
PDF ↗Large Language Models (LLMs) often exhibit social biases inherited from their training data. While existing benchmarks evaluate bias by term-based mode through direct term associations between demographic terms and bias terms, LLMs have become increasingly adept at avoiding biased responses, leading to seemingly low levels of bias. However, biases persist in subtler, contextually hidden forms that traditional benchmarks fail to capture. We introduce the Description-based Bias Benchmark (DBB), a novel dataset designed to assess bias at the semantic level that bias concepts are hidden within naturalistic, subtly framed contexts in real-world scenarios rather than superficial terms. We analyze six state-of-the-art LLMs, revealing that while models reduce bias in response at the term level, they continue to reinforce biases in nuanced settings. Data, code, and results are available at https://github.com/JP-25/Description-based-Bias-Benchmark.
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
PDF ↗Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity and strong performance, notably eliminating the need for a learned value function. However, GRPO implicitly assumes a balanced domain distribution and uniform semantic alignment across groups—assumptions that rarely hold in real-world datasets. When applied to multi-domain, imbalanced data, GRPO disproportionately optimizes for dominant domains, neglecting underrepresented ones and resulting in poor generalization and fairness. We propose Domain-Informed Self-Consistency Policy Optimization (DISCO), a principled extension to GRPO that addresses inter-group imbalance with two key innovations. Domain-aware reward scaling counteracts frequency bias by reweighting optimization based on domain prevalence. Difficulty-aware reward scaling leverages prompt-level self-consistency to identify and prioritize uncertain prompts that offer greater learning value. Together, these strategies promote more equitable and effective policy learning across domains. Extensive experiments across multiple LLMs and skewed training distributions show that DISCO improves generalization, outperforms existing GRPO variants by 5% on Qwen3 models, and sets new state-of-the-art results on multi-domain alignment benchmarks.
How does the natural evolution of context paragraphs affect Question Answering (QA) in generative Large Language Models (LLMs)? To address this, we propose a framework for curating naturally evolved, human-edited variants of reading passages from contemporary QA benchmarks and for analysing LLM performance across a range of semantic similarity scores, which quantify how closely each variant aligns with Wikipedia content on the same article topic that the LLM saw during pretraining. Using this framework, we evaluate 6 QA datasets and 8 LLMs with publicly available training data. Our experiments reveal that LLM performance declines as reading passages naturally diverge from the versions encountered during pretraining–even when the question and all necessary information remains present at inference time. For instance, average accuracy on BoolQ drops by over 30% from the highest to lowest similarity bins. This finding suggests that natural text evolution may pose a significant challenge to the language understanding capabilities of fully open-source LLMs.
English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge
PDF ↗Large language models (LLMs) excel in many tasks, but their safety guarantees vary by language, e.g., responses in English tend to be safer than those in low-resource languages. This inconsistency creates a vulnerability, since an attacker can circumvent safety measures by using a less-supported language as an intermediary, even without fluency in that language. Traditional solutions rely on multilingual safety alignment, which demands vast, per-language datasets and introduces significant trade-offs between usefulness and safety (the so-called “alignment tax”). To overcome these limitations, we introduce English as Defense Proxy (E-Proxy), a unified approach that leverages English, usually the advantage language of LLMs, as a universal safety anchor. During multilingual training, E-Proxy uses English jailbreak prompts to extract the model’s existing safety knowledge, then applies simple language-mapping prompts (e.g., “Please answer in target language”) to transfer that knowledge across languages. Our analysis shows that formulating prompts in a high-resource language preserves the model’s utility, while enforcing responses in the target language significantly enhances safety. We evaluate E-Proxy on extensive benchmarks of both attack resistance and task performance. On the MultiJail benchmark, E-Proxy blocks over 99 % of jailbreak attempts while retaining 95 % of average task performance, all with a simply constructed multilingual alignment data.
This paper studies the problem of time series forecasting, which aims to generate future predictions given historical trajectories. Recent researchers have applied large language models (LLMs) into time series forecasting, which usually align the time series space with textual space and output future predictions with strong autoregressive reasoning abilities. Despite their remarkable progress, these approaches usually lack an understanding of holistic temporal patterns with potential error accumulation. Towards this end, this paper proposes a simple yet effective framework that marries \underline{\text{L}}arg\underline{\text{e}} Langu\underline{\text{a}}ge Diffusion Model with time series \underline{\text{f}}orecasting (LEAF). The core of our framework is to generate future predictions with a diffusion model from a holistic view. In particular, we first introduce a tokenization module to convert time series into tokens and then adopt the language diffusion models to capture the temporal dependencies. In this way, we can transform masked time series into all the predictions with the remasking strategy. Extensive experiments on various benchmark datasets validate the effectiveness of the proposed LEAF in comparison to various baselines.
Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning
PDF ↗Recent advances in reasoning language models have witnessed a paradigm shift from short to long CoT pattern. Given the substantial computational cost of rollouts in long CoT models, maximizing the utility of fixed training datasets becomes crucial. Our analysis reveals that negative responses contain valuable components such as self-reflection and error-correction steps, yet primary existing methods either completely discard negative samples (RFT) or apply equal penalization across all tokens (RL), failing to leverage these potential learning signals. In light of this, we propose Behavior Constrained Policy Gradient with Negative Sample Augmentation (BCPG-NSA), a fine-grained offline RL framework that encompasses three stages: 1) sample segmentation, 2) consensus-based step correctness assessment combining LLM and PRM judgers, and 3) policy optimization with NSA designed to effectively mine positive steps within negative samples. Experimental results show that BCPG-NSA outperforms baselines on several challenging math/coding reasoning benchmarks using the same training dataset, achieving improved sample efficiency and demonstrating robustness and scalability when extended to multiple iterations.
Large Language Models (LLMs) offer transformative potential across diverse fields, yet their safe and effective deployment is hindered by inherent knowledge conflicts—stemming from temporal evolution, divergent sources, and contradictory guidelines. This challenge is particularly acute in medicine, an interdisciplinary frontier for NLP. Rapid medical concept drift can lead LLMs to provide incorrect or outdated advice, impacting their utility and the broader societal benefits of NLP advances. This study introduces ConflictMedQA, a benchmark designed to systematically evaluate how LLMs manage varied knowledge conflicts in clinical guidelines. Our assessment of seven state-of-the-art models across 4,290 scenarios reveals significant difficulties in rejecting incorrect recommendations and frequent endorsement of conflicting advice, highlighting an important gap for NLP systems intended for real-world impact. We explore two fundamental mitigation approaches: retrieval-augmented generation and preference fine-tuning via direct preference optimization. While each offers improvements, their synergistic combination yields the best results. These findings emphasize the need for LLMs to discern subtle but critical guideline conflicts. This is a crucial step in advancing NLP’s capabilities and ensuring its dependable application in critical societal domains. The proposed dataset is available at https://huggingface.co/datasets/RDBH/DriftMed.