Large language models (LLMs) have achieved remarkable success in natural language processing (NLP), demonstrating significant capabilities in processing and understanding text data. However, recent studies have identified limitations in LLMs' ability to reason about graph-structured data. To address this gap, we introduce GraphEval2000, the first comprehensive graph dataset, comprising 40 graph data structure problems along with 2000 test cases. Additionally, we introduce an evaluation framework based on GraphEval2000, designed to assess the graph reasoning abilities of LLMs through coding challenges. Our dataset categorizes test cases into four primary and four sub-categories, ensuring a comprehensive evaluation. We evaluate eight popular LLMs on GraphEval2000, revealing that LLMs exhibit a better understanding of directed graphs compared to undirected ones. While private LLMs consistently outperform open-source models, the performance gap is narrowing. Furthermore, to improve the usability of our evaluation framework, we propose Structured Symbolic Decomposition (SSD), an instruction-based method designed to enhance LLM performance on GraphEval2000. Results show that SSD improves the performance of GPT-3.5, GPT-4, and GPT-4o on complex graph problems, with an increase of 11.11\%, 33.37\%, and 33.37\%, respectively.

Current research found the issue of Early Answering in large language models (LLMs), where the models already have an answer before generating the Chain-of-Thought (CoT). This phenomenon suggests a potential lack of necessary dependency between the predicted answer and the reasoning process. Consequently, two important questions arise: (1) Is CoT still necessary if the model already has an answer? (2) Can the correctness of the answer serve as valid evidence for the correctness of CoT? To address these questions, we propose a method, namely Chain-of-Probe (CoP), to probe changes in the mind during the model's reasoning. The probing results show that in a significant number of question-answer cases, CoT appears to be unnecessary, and this necessity correlates with the simplicity of the task, defined by reasoning steps required. Furthermore, by analyzing patterns in mind change, we examine the correctness of the model's reasoning. Our validation reveals that many responses, although correct in their final answer, contain errors in their reasoning process. To this end, we propose a strategic approach based on CoP to prioritize answers with correct reasoning among multiple candidates, thereby bolstering the reliability of the model's reasoning.

Multi-step reasoning is widely adopted in the community to explore the better performance of language models (LMs). We report on the systematic strategy that LMs use in this process. Our controlled experiments reveal that LMs rely more heavily on heuristics, such as lexical overlap, in the earlier stages of reasoning Figure 1: Illustration of the systematic strategy we discovered when more steps are required to reach an in language models (LMs). When the goal is answer. Conversely, as LMs progress closer distant from the current state in a multi-step reasoning to the final answer, their reliance on heuristics process, the models tend to rely on heuristics, such as decreases. This suggests that LMs track only superficial overlap, which can lead them in the wrong a limited number of future steps and dynamically direction. In contrast, when the goal is within a limited combine heuristic strategies with logical distance, the models are more likely to take rational actions ones in tasks involving multi-step reasoning.

Recent literature has highlighted potential risks to academic integrity associated with large language models (LLMs), as they can memorize parts of training instances and reproduce them in the generated texts without proper attribution. In addition, given their capabilities in generating high-quality texts, plagiarists can exploit LLMs to generate realistic paraphrases or summaries indistinguishable from original work. In response to possible malicious use of LLMs in plagiarism, we introduce PlagBench, a comprehensive dataset consisting of 46.5K synthetic plagiarism cases generated using three instruction-tuned LLMs across three writing domains. The quality of PlagBench is ensured through fine-grained automatic evaluation for each type of plagiarism, complemented by human annotation. We then leverage our proposed dataset to evaluate the plagiarism detection performance of five modern LLMs and three specialized plagiarism checkers. Our findings reveal that GPT-3.5 tends to generates paraphrases and summaries of higher quality compared to Llama2 and GPT-4. Despite LLMs' weak performance in summary plagiarism identification, they can surpass current commercial plagiarism detectors. Overall, our results highlight the potential of LLMs to serve as robust plagiarism detection tools.

Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely on language descriptions as inputs. However, it remains unclear how well LLMs can function as few-shot or zero-shot embodied agents in dynamic interactive environments. To address this gap, we introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE (i) offers adaptability to diverse environments without multiple simulation engines, (ii) evaluates agents' capacity to develop ``internalized world knowledge'' with embodied observations, and (iii) allows easy customization of communication and action strategies. To address the embodiment challenge, we devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information. Comprehensive benchmark results illustrate challenges and insights of embodied planning. LangSuitE represents a significant step toward building embodied generalists in the context of language models.

Large language models (LLMs), despite their breakthroughs on many challenging benchmark tasks, lean to generate verbose responses and lack the controllability of output complexity, which is usually preferred by human users in practice. In this paper, we study how to precisely control multiple linguistic complexities of LLM output by finetuning using off-the-shelf data. To this end, we propose multi-control tuning (MCTune), which includes multiple linguistic complexity values of ground-truth responses as controls in the input for instruction tuning. We finetune LLaMA2-7B on Alpaca-GPT4 and WizardLM datasets. Evaluations on widely used benchmarks demonstrate that our method does not only improve LLMs' multi-complexity controllability substantially but also retains or even enhances the quality of the responses as a side benefit.

Membership inference (MI) attacks try to determine if a data sample was used to train a machine learning model. For foundation models trained on unknown Web data, MI attacks can be used to detect copyrighted training materials, measure test set contamination, or audit machine unlearning. Unfortunately, we find that evaluations of MI attacks for foundation models are flawed, because they sample members and non-members from different distributions. For 8 published MI evaluation datasets, we show that blind attacks -- that distinguish the member and non-member distributions without looking at any trained model -- outperform state-of-the-art MI attacks. Existing evaluations thus tell us nothing about membership leakage of a foundation model's training data.

Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being In-Context Learning (ICL). With ICL, LLMs can derive the underlying rule from a few demonstrations and provide answers that comply with the rule. Previous work hypothesized that the network creates a "task vector" in specific positions during ICL. Patching the "task vector" allows LLMs to achieve zero-shot performance similar to few-shot learning. However, we discover that such "task vectors" do not exist in tasks where the rule has to be defined through multiple demonstrations. Instead, the rule information provided by each demonstration is first transmitted to its answer position and forms its own rule vector. Importantly, all the rule vectors contribute to the output in a distributed manner. We further show that the rule vectors encode a high-level abstraction of rules extracted from the demonstrations. These results are further validated in a series of tasks that rely on rules dependent on multiple demonstrations. Our study provides novel insights into the mechanism underlying ICL in LLMs, demonstrating how ICL may be achieved through an information aggregation mechanism.

Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. We introduce FastMem, a novel method designed to enhance instruction fine-tuned LLMs' context awareness through fast memorization of the prompt. FastMem maximizes the likelihood of the prompt before inference by fine-tuning only the last Feed-Forward Network (FFN) module. This targeted approach ensures efficient optimization without overfitting, significantly improving the model's ability to comprehend and accurately follow the context. Our experiments demonstrate substantial gains in reading comprehension, text summarization and adherence to output structures. For instance, FastMem improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6%, and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%. Extensive experimental results highlight FastMem's potential to offer a robust solution to enhance the reliability and accuracy of LLMs in various applications. Our code is available at: https://github.com/IAAR-Shanghai/FastMem

Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art LLMs on inherently crosslingual tasks. We observe that while these models show promising surface-level crosslingual abilities on machine translation and embedding space analyses, they struggle with deeper crosslingual knowledge transfer, revealing a crosslingual knowledge barrier in both general (MMLU benchmark) and domain-specific (Harry Potter quiz) contexts. We observe that simple inference-time mitigation methods offer only limited improvement. On the other hand, we propose fine-tuning of LLMs on mixed-language data, which effectively reduces these gaps, even when using out-of-domain datasets like WikiText. Our findings suggest the need for explicit optimization to unlock the full crosslingual potential of LLMs.