Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have demonstrated that these models implicitly embed reasoning trees, humans typically employ various distinct logical reasoning mechanisms to complete the same task. It is still unclear which multi-step reasoning mechanisms are used by language models to solve such tasks. In this paper, we aim to address this question by investigating the mechanistic interpretability of language models, particularly in the context of multi-step reasoning tasks. Specifically, we employ circuit analysis and self-influence functions to evaluate the changing importance of each token throughout the reasoning process, allowing us to map the reasoning paths adopted by the model. We apply this methodology to the GPT-2 model on a prediction task (IOI) and demonstrate that the underlying circuits reveal a human-interpretable reasoning process used by the model.

Knowledge Editing-Efficiently modifying the knowledge in large language models has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge. However, we argue that these benchmarks fail to effectively evaluate how well the updated models apply this knowledge in real-life scenarios, particularly when questions require complex reasoning involving one-to-many relationships or multi-step logical intersections. To fill in this gap, we introduce a new benchmark, COMPKE: Complex Question Answering under Knowledge Editing, which includes 11,924 complex questions that reflect real-life situations. We perform a comprehensive evaluation of four different knowledge editing methods in COMPKE, and our results show that the performance of these methods varies between different models. For example, MeLLo achieves an accuracy of 39.47 on GPT-4o-mini but drops significantly to 3.83 on Qwen2.5-3B. We further analyze the reasons behind these results from both methodological and model perspectives. Our dataset will be publicly available on GitHub.

Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored. In this work, we propose a novel benchmark, : Code Migration Across Environment, designed to evaluate LLMs’ performance in handling code migration tasks. The benchmark comprises 922 data points across 19 Python and Java packages, offering three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments. Experimental evaluation of across seven LLMs revealed an average pass@1 rate of 26.50%, with GPT-4o performing best at 43.84%. We highlight our key findings as follows: (i) LLMs are more familiar with newer function versions, making them better at migrating legacy code, and (ii) a logical inconsistency where LLMs sometimes identify irrelevant function changes for the target migration environment.

With the increasing integration of large language models (LLMs) into real-world applications such as finance, e-commerce, and recommendation systems, their susceptibility to misinformation and adversarial manipulation poses significant risks. Existing fraud detection benchmarks primarily focus on single-turn classification tasks, failing to capture the dynamic nature of real-world fraud attempts. To address this gap, we introduce Fraud-R1, a challenging bilingual benchmark designed to assess LLMs’ ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships, covering subclasses. Our dataset comprises manually curated fraud cases from social media, news, phishing scam records, and prior fraud datasets.

Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”. While previous studies have proposed decoding strategies to mitigate repetition, the underlying mechanism behind this issue remains insufficiently explored. In this work, we investigate the root causes of repetition in LLMs through the lens of mechanistic interpretability. Inspired by recent advances in Sparse Autoencoders (SAEs), which enable monosemantic feature extraction, we propose a novel approach—”Duplicatus Charm”—to induce and analyze the Repeat Curse. Our method systematically identifies “Repetition Features” -the key model activations responsible for generating repetitive outputs. First, we locate the layers most involved in repetition through logit analysis. Next, we extract and stimulate relevant features using SAE-based activation manipulation. To validate our approach, we construct a repetition dataset covering token and paragraph level repetitions and introduce an evaluation pipeline to quantify the influence of identified repetition features. Furthermore, by deactivating these features, we have effectively mitigated the Repeat Curse.

Fine-tuning-based unlearning methods prevail for erasing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of the methods is unclear. In this paper, we delve into the limitations of fine-tuning-based unlearning through activation patching and parameter restoration experiments. Our findings reveal that these methods alter the model’s knowledge retrieval process, rather than genuinely erasing the problematic knowledge embedded in the model parameters. Furthermore, behavioral tests demonstrate that the unlearning mechanisms inevitably impact the global behavior of the models, affecting unrelated knowledge or capabilities. Our work advocates the development of more resilient unlearning techniques for truly erasing knowledge.

Recently it has been shown that deep learning models for NLP tasks are prone to attacks that can even reconstruct the verbatim training texts. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the formal guarantees of differential privacy (DP) in the embedding space. However, many existing approaches either achieve unsatisfactory performance in the high privacy regime when using the Laplacian or Gaussian mechanism, or resort to weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength. This raises the question of whether a new method for private word embedding can be designed to overcome these limitations. In this paper, we propose a novel private embedding method called the high dimensional truncated Laplacian mechanism. Specifically, we introduce a non-trivial extension of the truncated Laplacian mechanism, which was previously only investigated in one-dimensional space cases. Theoretically, we show that our method has a lower variance compared to the previous private word embedding methods. To further validate its effectiveness, we conduct comprehensive experiments on private embedding and downstream tasks using three datasets. Remarkably, even in the high privacy regime, our approach only incurs a slight decrease in utility compared to the non-private scenario.

Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance while also protecting the privacy of sensitive data is a crucial challenge in NLP. To preserve privacy, Differential Privacy (DP), which can prevent reconstruction attacks and protect against potential side knowledge, is becoming a de facto technique for private data analysis. In recent years, NLP in DP models (DP-NLP) has been studied from different perspectives, which deserves a comprehensive review. In this paper, we provide the first systematic review of recent advances in DP deep learning models in NLP. In particular, we first discuss some differences and additional challenges of DP-NLP compared with the standard DP deep learning. Then, we investigate some existing work on DP-NLP andpresent its recent developments from three aspects: gradient perturbation based methods, embedding vector perturbation based methods, and ensemble model based methods. We also discuss some challenges and future directions.

Multimodal emotion recognition in conversation (MERC) and multimodal emotion-cause pair extraction (MECPE) have recently garnered significant attention. Emotions are the expression of affect or feelings; responses to specific events, or situations – known as emotion causes. Both collectively explain the causality between human emotion and intents. However, existing works treat emotion recognition and emotion cause extraction as two individual problems, ignoring their natural causality. In this paper, we propose a Unified Multimodal Emotion recognition and Emotion-Cause analysis framework (UniMEEC) to explore the causality between emotion and emotion cause. Concretely, UniMEEC reformulates the MERC and MECPE tasks as mask prediction problems and unifies them with a causal prompt template. To differentiate the modal effects, UniMEEC proposes a multimodal causal prompt to probe the pre-trained knowledge specified to modality and implements cross-task and cross-modality interactions under task-oriented settings. Experiment results on four public benchmark datasets verify the model performance on MERC and MECPE tasks and achieve consistent improvements compared with the previous state-of-the-art methods.