论文检索

Huy Nghiem, Hal Daumé III

The widespread use of social media necessitates reliable and efficient detection of offensive content to mitigate harmful effects. Although sophisticated models perform well on individual datasets, they often fail to generalize due to varying definitions and labeling of “offensive content.” In this paper, we introduce HateCOT, an English dataset with over 52,000 samples from diverse sources, featuring explanations generated by GPT-3.5Turbo and curated by humans. We demonstrate that pretraining on HateCOT significantly enhances the performance of open-source Large Language Models on three benchmark datasets for offensive content detection in both zero-shot and few-shot settings, despite differences in domain and task. Additionally, HateCOT facilitates effective K-shot fine-tuning of LLMs with limited data and improves the quality of their explanations, as confirmed by our human evaluation.

Yasaman Razeghi, Ishita Dasgupta, Fangyu Liu, Vinay Venkatesh Ramasesh, Sameer Singh

Recent advances in multimodal models show remarkable performance in real-world benchmarks for chart and figure understanding like ChartQA that involve interpreting trends, comparing data points, and extracting insights from visuals.In this paper, we investigate the extent to which these models truly comprehend the underlying information in charts by posing direct, elementary questions about simple features such as axes ranges and values to examine their fundamental visual understanding abilities in the context of charts.Our questions are applied to two sets of figures: synthetic and real-world.The empirical evaluation of 5 popular multimodal models on our dataset reveals shortfalls in understanding charts and figures, contrary to what their performance on complex benchmarks might suggest.For instance, Gemini Pro Vision only achieves 57.9% accuracy on our elementary set of questions on real-world plots, while other popular multimodal models showed similar or less performance.This work highlights an important limitation of current multimodal models, and cautions against overly optimistic interpretations of their abilities based on results of canonical evaluations.

Mayank Singh, Eduardo Blanco

We propose a neuro-symbolic approach for realistic few-shot relation classification via rules. Instead of building neural models to predict relations, we design them to output straightforward rules that can be used to extract relations. The rules are generated using custom T5-style Encoder-Decoder Language Models. Crucially, our rules are fully interpretable and pliable (i.e., humans can easily modify them to boost performance). Through a combination of rules generated by these models along with a very effective, novel baseline, we demonstrate a few-shot relation-classification performance that is comparable to or stronger than the state of the art on the Few-Shot TACRED and NYT29 benchmarks while increasing interpretability and maintaining pliability.

Hanfeng Liu, Minping Chen, Zhenya Zheng, Zeyi Wen

Aspect-term sentiment analysis (ATSA) identifies fine-grained sentiments towards specific aspects of the text. While pre-trained language models (PLMs) have set the state-of-the-art (SOTA) for ATSA, they are resource-intensive due to their large model sizes, restricting their wide applications to resource-constrained scenarios. Conversely, conventional machine learning methods, such as Support Vector Machines (SVMs), offer the benefit of less resource requirement but have lower predictive accuracy. This paper introduces an innovative pipeline, termed SVM-ATSA, which bridges the gap between the accuracy of SVM-based methods and the efficiency of PLM-based methods. To improve the feature expression of SVMs and better adapt to the ATSA task, SVM-ATSA decomposes the learning problem into multiple view subproblems, and dynamically selects as well as constructs features with reinforcement learning. The experimental results demonstrate that SVM-ATSA surpasses SOTA PLM-based methods in predictive accuracy while maintaining a faster inference speed and significantly reducing the number of model parameters.

Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Byzantine-resistant aggregations detect poisonous clients and discard them to ensure that the global model is not poisoned or attacked by malicious clients. However, these aggregations are mainly conducted on the parameter space, and the parameter distances cannot reflect the data distribution divergences between clients. Therefore, existing Byzantine-resistant aggregations cannot defend against backdoor injection by malicious attackers in federated natural language tasks. In this paper, we propose the client embedding for malicious client detection to enhance Byzantine-resistant aggregations. The distances between client embeddings are required to reflect the data distribution divergences of the corresponding clients. Experimental results validate the effectiveness of the proposed client embeddings.

Xiangyu Hong, Che Jiang, Biqing Qi, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou

Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown promising results in extending the context length of language models. However, understanding how position embedding can capture longer-range contextual information remains elusive. Based on the intuition that different dimensions correspond to different frequency of changes in RoPE encoding, we conducted a dimension-level analysis to investigate the correlation between a hidden dimension of an attention head and its contribution to capturing long-distance dependencies. Using our correlation metric, we identified a particular type of attention heads, which we named Positional Heads, from various length-extrapolated models. These heads exhibit a strong focus on long-range information interaction and play a pivotal role in long input processing, as evidence by our ablation. We further demonstrate the correlation between the efficiency of length extrapolation and the extension of the high-dimensional attention allocation of these heads. The identification of Positional Heads provides insights for future research in long-text comprehension.

Michael Ginn, Mans Hulden, Alexis Palmer

Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use.

Puli Chen, Cheng Yang, Qingbao Huang

Metaphor, as an advanced form of cognition, is challenging to understand their meaning. Current metaphor detection tasks only provide labels (i.e., metaphor or literal) without interpreting how to understand them. In this paper, we improve the metaphor detection task and explore the reason of metaphor. To the best of our knowledge, we are the first work to reason about metaphor using mainstream Large Language Models (LLMs). Specifically, we utilized ChatGPT3.5 to expand the mainstream datasets in current metaphor detection, including VUA ALL, TroFi, and MOH-X. We input the original sentence, target word, and usage (metaphor or literal) into ChatGPT, guiding it to generate corresponding metaphor reason. Then, we designed supervised baseline experiments (e.g., RoBERTa, GPT-2) and zero-shot experiments with LLMs (e.g., LLaMA3). For the results generated by the above experiments, we provided the case study. We devised four methods that include manual evaluation to evaluate the reason performance of the model, and discussed extensively the advantages and disadvantages of these evaluation methods. Our code is available at https://github.com/yc-cy/Metaphorical-Reasoning.

Yu Chen, Qi Cao, Kaike Zhang, Xuchao Liu, Huawei Shen

In textual backdoor attacks, attackers insert poisoned samples with triggered inputs and target labels into training datasets to manipulate model behavior, threatening the model’s security and reliability. Current defense methods can generally be categorized into inference-time and training-time ones. The former often requires a part of clean samples to set detection thresholds, which may be hard to obtain in practical application scenarios, while the latter usually requires an additional retraining or unlearning process to get a clean model, significantly increasing training costs. To avoid these drawbacks, we focus on developing a practical defense method before model training without using any clean samples. Our analysis reveals that with the help of a pre-trained language model (PLM), poisoned samples, different from clean ones, exhibit mismatched relationship and shared characteristics. Based on these observations, we further propose a two-stage poison detection strategy solely leveraging insights from PLM before model training. Extensive experiments confirm our approach’s effectiveness, achieving better performance than current leading methods more swiftly. Our code is available at https://github.com/Ascian/PKAD.

Si Chen, Feiyang Kang, Ning Yu, Ruoxi Jia

Fact tracing seeks to identify specific training examples that serve as the knowledge source for a given query. Existing approaches to fact tracing rely on assessing the similarity between each training sample and the query along a certain dimension, such as lexical similarity, gradient, or embedding space. However, these methods fall short of effectively distinguishing between samples that are merely relevant and those that actually provide supportive evidence for the information sought by the query. This limitation often results in suboptimal effectiveness. Moreover, these approaches necessitate the examination of the similarity of individual training points for each query, imposing significant computational demands and creating a substantial barrier for practical applications. This paper introduces FASTTRACK, a novel approach that harnesses the capabilities of Large Language Models (LLMs) to validate supportive evidence for queries and at the same time clusters the training database towards a reduced extent for LLMs to trace facts. Our experiments show that FASTTRACK substantially outperforms existing methods in both accuracy and efficiency, achieving more than 100% improvement in F1 score over the state-of-the-art methods while being x33 faster than TracIn.

Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao, Wenpeng Lu

The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods. Existing works primarily rely on external evaluators, focusing on training and prompting strategies. However, a crucial aspect – model-aware glass-box features – is overlooked. In this study, we explore the utility of glass-box features under the scenario of self-evaluation, namely applying an LLM to evaluate its own output. We investigate various glass-box feature groups and discovered that the softmax distribution serves as a reliable quality indicator for self-evaluation. Experimental results on public benchmarks validate the feasibility of self-evaluation of LLMs using glass-box features.

Sharon Levy, Tahilin Sanchez Karver, William Adler, Michelle R Kaufman, Mark Dredze

Chat-based large language models have the opportunity to empower individuals lacking high-quality healthcare access to receive personalized information across a variety of topics. However, users may ask underspecified questions that require additional context for a model to correctly answer. We study how large language model biases are exhibited through these contextual questions in the healthcare domain. To accomplish this, we curate a dataset of sexual and reproductive healthcare questions (ContextSRH) that are dependent on age, sex, and location attributes. We compare models’ outputs with and without demographic context to determine answer alignment among our contextual questions. Our experiments reveal biases in each of these attributes, where young adult female users are favored.

Sharon Levy, William Adler, Tahilin Sanchez Karver, Mark Dredze, Michelle R Kaufman

Large language models (LLMs) acquire beliefs about gender from training data and can therefore generate text with stereotypical gender attitudes. Prior studies have demonstrated model generations favor one gender or exhibit stereotypes about gender, but have not investigated the complex dynamics that can influence model reasoning and decision-making involving gender. We study gender equity within LLMs through a decision-making lens with a new dataset, DeMET Prompts, containing scenarios related to intimate, romantic relationships. We explore nine relationship configurations through name pairs across three name lists (men, women, neutral). We investigate equity in the context of gender roles through numerous lenses: typical and gender-neutral names, with and without model safety enhancements, same and mixed-gender relationships, and egalitarian versus traditional scenarios across various topics. While all models exhibit the same biases (women favored, then those with gender-neutral names, and lastly men), safety guardrails reduce bias. In addition, models tend to circumvent traditional male dominance stereotypes and side with “traditionally female” individuals more often, suggesting relationships are viewed as a female domain by the models.

Xianming Li, Jing Li

Social media data exhibits severe redundancy caused by its noisy nature. It leads to increased training time and model bias in its processing. To address this issue, we propose a novel Generative Deduplication framework for social media data selection by removing semantically duplicate data. While related work involves data selection in the task-specific training, our model functions as an efficient pre-processing method to universally enhance social media NLP pipelines. Specifically, we train a generative model via self-supervised learning to predict keyword to capture the semantics of noisy social media text for deduplication. Meanwhile, time-dimensional Gaussian noise is added to improve training complexity and avoid learning trivial features. Extensive experiments suggest that our model can better reduce training samples while improving performance than baselines. The results show our model’s potential to broadly advance social media language understanding in effectiveness and efficiency.

Meng Lu, Brandon Ho, Dennis Ren, Xuan Wang

The global escalation in emergency department patient visits poses significant challenges to efficient clinical management, particularly in clinical triage. Traditionally managed by human professionals, clinical triage is susceptible to substantial variability and high workloads. Although large language models (LLMs) demonstrate promising reasoning and understanding capabilities, directly applying them to clinical triage remains challenging due to the complex and dynamic nature of the clinical triage task. To address these issues, we introduce TriageAgent, a novel heterogeneous multi-agent framework designed to enhance collaborative decision-making in clinical triage. TriageAgent leverages LLMs for role-playing, incorporating self-confidence and early-stopping mechanisms in multi-round discussions to improve document reasoning and classification precision for triage tasks. In addition, TriageAgent employs the medical Emergency Severity Index (ESI) handbook through a retrieval-augmented generation (RAG) approach to provide precise clinical knowledge and integrates both coarse- and fine-grained ESI-level predictions in the decision-making process. Extensive experiments demonstrate that TriageAgent outperforms state-of-the-art LLM-based methods on three clinical triage test sets. Furthermore, we have released the first public benchmark dataset for clinical triage with corresponding ESI levels and human expert performance for comparison.

Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek F. Wong, Rui Wang

Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models (LLMs) have demonstrated impressive general understanding and generation abilities, their potential in multi-domain MT is under-explored. We establish a comprehensive benchmark for multi-domain translation, featuring 25 German⇔English and 22 Chinese⇔English test sets respectively covering 15 domains. Our evaluation of prominent LLMs reveals a discernible performance gap against traditional MT systems, highlighting domain overfitting and catastrophic forgetting issues after fine-tuning on domain-limited corpora. To mitigate this, we propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance. This method inspires the LLM to perceive domain information from the source text, which then serves as a helpful hint to guide the translation process. Despite being trained on a small dataset of four domains, our CoT fine-tune approach achieves notable enhancements in translation accuracy and domain robustness than traditional fine-tuning, as evidenced by an average 1.53 BLEU score increase in over 20 German→English distinct out-of-domain tests.

Xiaoran Liu, Kai Lv, Qipeng Guo, Hang Yan, Conghui He, Xipeng Qiu, Dahua Lin

The quality of training data is crucial for enhancing the long-text capabilities of foundation models. Despite existing efforts to refine data quality through heuristic rules and evaluations based on data diversity and difficulty, there’s a lack of systematic approaches specifically tailored for assessing long texts. Addressing this gap, our work systematically measures the quality of long texts by evaluating three fundamental linguistic dimensions: coherence, cohesion, and complexity. Drawing inspiration from the aforementioned three dimensions, we introduce a suite of metrics designed to evaluate the quality of long texts, encompassing both statistical and pre-trained language model-based ones. Leveraging these metrics, we present LongWanjuan, a bilingual dataset specifically tailored to enhance the training of language models for long-text tasks with over 160B tokens. In LongWanjuan, we categorize long texts into holistic, aggregated, and chaotic types, enabling a detailed analysis of long-text quality. Furthermore, we devise a data mixture recipe that strategically balances different types of long texts within LongWanjuan, leading to significant improvements in model performance on long-text tasks.

Zhiqi Wang, Shizhu He, Kang Liu, Jun Zhao

Large language models perform well on tasks that have undergone fine-tuning of instructions, but their performance on completely unseen tasks is often less than ideal. To overcome the challenge of cross-task generalization, task-level LoRAs combination is proposed, which does not require training a model for new tasks. Instead, it learns the LoRA modules combination weights based on a small number of samples to form the task model. However, task-level LoRAs combination only utilizes a few task modules due to its reliance on the weight enumeration method, and it also ignores the specificity between different instances. Therefore, we proposed an instance-level LoRAs composition for cross-task generalization, which selects appropriate multiple task LoRA modules for each input instance and dynamically determines the composition weights. Our experiments on publicly available datasets show that our method outperforms the typical method, LoraHub, in 16 out of 27 tasks. We release the source code at https://github.com/noname822/iLoraComp.git

Zhige Huang, Haoan Jin, Mengyue Wu, Kenny Q. Zhu

Reconstructing ancient Chinese pronunciation is a challenging task due to the scarcity of phonetic records. Different from historical linguistics’ comparative approaches, we reformulate this problem into a temporal prediction task with masked language models, digitizing existing phonology rules into ACP (Ancient Chinese Phonology) dataset of 70,943 entries for 17,001 Chinese characters. Utilizing this dataset and Chinese character glyph information, our transformer-based model demonstrates superior performance on a series of reconstruction tasks, with or without prior phonological knowledge on the target historical period. Our work significantly advances the digitization and computational reconstruction of ancient Chinese phonology, providing a more complete and temporally contextualized resource for computational linguistics and historical research. The dataset and model training code are publicly available.

Pengyu Xu, Liping Jing, Jian Yu

Recent advancements in noisy multi-label text classification have primarily relied on the class-conditional noise (CCN) assumption, which treats each label independently undergoing label flipping to generate noisy labels. However, in real-world scenarios, noisy labels often exhibit dependencies with true labels. In this study, we validate through hypothesis testing that real-world datasets are unlikely to adhere to the CCN assumption, indicating that label noise is dependent on the labels. To address this, we introduce a label-specific denoising framework designed to counteract label-dependent noise. The framework initially presents a holistic selection metric that evaluates noisy labels by concurrently considering loss information, ranking information, and feature centroid. Subsequently, it identifies and corrects noisy labels individually for each label category in a fine-grained manner. Extensive experiments on benchmark datasets demonstrate the effectiveness of our method under both synthetic and real-world noise conditions, significantly improving performance over existing state-of-the-art models.