The task of code generation from natural language (NL2Code) has become extremely popular, especially with the advent of Large Language Models (LLMs). However, efforts to quantify and track this progress have suffered due to a lack of reliable metrics for functional correctness. While popular benchmarks like HumanEval have test cases to enable reliable evaluation of correctness, it is time-consuming and requires human effort to collect test cases. As an alternative several reference-based evaluation metrics have been proposed, with embedding-based metrics like CodeBERTScore being touted as having a high correlation with human preferences and functional correctness. In our work, we analyze the ability of embedding-based metrics like CodeBERTScore to measure functional correctness and other helpful constructs like editing effort by analyzing outputs of ten models over two popular code generation benchmarks. Our results show that while they have a weak correlation with functional correctness (0.16), they are strongly correlated (0.72) with editing effort.

Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms. How well LLMs accomplish event reasoning on various relations and reasoning paradigms remains unknown. To mitigate this disparity, we comprehensively evaluate the abilities of event reasoning of LLMs. We introduce a novel benchmark EV2 for EValuation of EVent reasoning. EV2 consists of two levels of evaluation of schema and instance and is comprehensive in relations and reasoning paradigms. We conduct extensive experiments on EV2. We find that LLMs have abilities to accomplish event reasoning but their performances are far from satisfactory. We also notice the imbalance of event reasoning abilities in LLMs. Besides, LLMs have event schema knowledge, however, they're not aligned with humans on how to utilize the knowledge. Based on these findings, we introduce two methods to guide the LLMs to utilize the event schema knowledge. Both methods achieve improvements.

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG) technique. However, these frameworks' designs do not have sufficient consideration of the risk of external content, thereby allowing attackers to undermine the applications developed with these frameworks. In this paper, we reveal a new threat to LLM-powered applications, termed retrieval poisoning, where attackers can guide the application to yield malicious responses during the RAG process. Specifically, through the analysis of LLM application frameworks, attackers can craft documents visually indistinguishable from benign ones. Despite the documents providing correct information, once they are used as reference sources for RAG, the application is misled into generating incorrect responses. Our preliminary experiments indicate that attackers can mislead LLMs with an 88.33\% success rate, and achieve a 66.67\% success rate in the real-world application, demonstrating the potential impact of retrieval poisoning.

Background: Recent advancements in Artificial Intelligence (AI) contributed significantly to suicide assessment, however, our theoretical understanding of this complex behavior is still limited. Objective: This study aimed to harness AI methodologies to uncover hidden risk factors that trigger or aggravate suicide behaviors. Method: The primary dataset included 228,052 Facebook postings by 1,006 users who completed the gold-standard Columbia Suicide Severity Rating Scale. This dataset was analyzed using a bottom-up research pipeline without a-priory hypotheses and its findings were validated using a top-down analysis of a new dataset. This secondary dataset included responses by 1,062 participants to the same suicide scale as well as to well-validated scales measuring depression and boredom. Results: An almost fully automated, AI-guided research pipeline resulted in four Facebook topics that predicted the risk of suicide, of which the strongest predictor was boredom. A comprehensive literature review using APA PsycInfo revealed that boredom is rarely perceived as a unique risk factor of suicide. A complementing top-down path analysis of the secondary dataset uncovered an indirect relationship between boredom and suicide, which was mediated by depression. An equivalent mediated relationship was observed in the primary Facebook dataset as well. However, here, a direct relationship between boredom and suicide risk was also observed. Conclusions: Integrating AI methods allowed the discovery of an under-researched risk factor of suicide. The study signals boredom as a maladaptive 'ingredient' that might trigger suicide behaviors, regardless of depression. Further studies are recommended to direct clinicians' attention to this burdening, and sometimes existential experience.

The advent of Large Language Models (LLM) provides new insights to validate Automated Driving Systems (ADS). In the herein-introduced work, a novel approach to extracting scenarios from naturalistic driving datasets is presented. A framework called Chat2Scenario is proposed leveraging the advanced Natural Language Processing (NLP) capabilities of LLM to understand and identify different driving scenarios. By inputting descriptive texts of driving conditions and specifying the criticality metric thresholds, the framework efficiently searches for desired scenarios and converts them into ASAM OpenSCENARIO and IPG CarMaker text files. This methodology streamlines the scenario extraction process and enhances efficiency. Simulations are executed to validate the efficiency of the approach. The framework is presented based on a user-friendly web app and is accessible via the following link: https://github.com/ftgTUGraz/Chat2Scenario.

Counterfactual text generation aims to minimally change a text, such that it is classified differently. Judging advancements in method development for counterfactual text generation is hindered by a non-uniform usage of data sets and metrics in related work. We propose CEval, a benchmark for comparing counterfactual text generation methods. CEval unifies counterfactual and text quality metrics, includes common counterfactual datasets with human annotations, standard baselines (MICE, GDBA, CREST) and the open-source language model LLAMA-2. Our experiments found no perfect method for generating counterfactual text. Methods that excel at counterfactual metrics often produce lower-quality text while LLMs with simple prompts generate high-quality text but struggle with counterfactual criteria. By making CEval available as an open-source Python library, we encourage the community to contribute more methods and maintain consistent evaluation in future work.

Ensuring the privacy of Large Language Models (LLMs) is becoming increasingly important. The most widely adopted technique to accomplish this is DP-SGD, which trains a model to guarantee Differential Privacy (DP). However, DP-SGD overestimates an adversary's capabilities in having white box access to the model and, as a result, causes longer training times and larger memory usage than SGD. On the other hand, commercial LLM deployments are predominantly cloud-based; hence, adversarial access to LLMs is black-box. Motivated by these observations, we present Private Mixing of Ensemble Distributions (PMixED): a private prediction protocol for next-token prediction that utilizes the inherent stochasticity of next-token sampling and a public model to achieve Differential Privacy. We formalize this by introducing RD-mollifers which project each of the model's output distribution from an ensemble of fine-tuned LLMs onto a set around a public LLM's output distribution, then average the projected distributions and sample from it. Unlike DP-SGD which needs to consider the model architecture during training, PMixED is model agnostic, which makes PMixED a very appealing solution for current deployments. Our results show that PMixED achieves a stronger privacy guarantee than sample-level privacy and outperforms DP-SGD for privacy $\epsilon = 8$ on large-scale datasets. Thus, PMixED offers a practical alternative to DP training methods for achieving strong generative utility without compromising privacy.

While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbolic planners for solving complex decision making tasks. In this work, we demonstrate how to train Transformers to solve complex planning tasks. This is accomplished by training an encoder-decoder Transformer model to predict the search dynamics of the $A^*$ search algorithm. We fine tune this model to obtain a Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93.7% of the time, while using up to 26.8% fewer search steps than the $A^*$ implementation that was used for training initially. In our training method, $A^*$'s search dynamics are expressed as a token sequence outlining when task states are added and removed into the search tree during symbolic planning. Searchformer significantly outperforms baselines that predict the optimal plan directly with a 5-10$\times$ smaller model size and a 10$\times$ smaller training dataset. Lastly, we demonstrate how Searchformer scales to larger and more complex decision making tasks with improved percentage of solved tasks and shortened search dynamics.

This research explores the application of Large Language Models (LLMs) for automating the extraction of requirement-related legal content in the food safety domain and checking legal compliance of regulatory artifacts. With Industry 4.0 revolutionizing the food industry and with the General Data Protection Regulation (GDPR) reshaping privacy policies and data processing agreements, there is a growing gap between regulatory analysis and recent technological advancements. This study aims to bridge this gap by leveraging LLMs, namely BERT and GPT models, to accurately classify legal provisions and automate compliance checks. Our findings demonstrate promising results, indicating LLMs' significant potential to enhance legal compliance and regulatory analysis efficiency, notably by reducing manual workload and improving accuracy within reasonable time and financial constraints.

Prompt leakage in large language models (LLMs) poses a significant security and privacy threat, particularly in retrieval-augmented generation (RAG) systems. However, leakage in multi-turn LLM interactions along with mitigation strategies has not been studied in a standardized manner. This paper investigates LLM vulnerabilities against prompt leakage across 4 diverse domains and 10 closed- and open-source LLMs. Our unique multi-turn threat model leverages the LLM's sycophancy effect and our analysis dissects task instruction and knowledge leakage in the LLM response. In a multi-turn setting, our threat model elevates the average attack success rate (ASR) to 86.2%, including a 99% leakage with GPT-4 and claude-1.3. We find that some black-box LLMs like Gemini show variable susceptibility to leakage across domains - they are more likely to leak contextual knowledge in the news domain compared to the medical domain. Our experiments measure specific effects of 6 black-box defense strategies, including a query-rewriter in the RAG scenario. Our proposed multi-tier combination of defenses still has an ASR of 5.3% for black-box LLMs, indicating room for enhancement and future direction for LLM security research.