Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (e.g., developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, when both code solutions and test cases are plausible and not reliable, selecting the best solution becomes challenging. Although some heuristic strategies have been proposed to tackle this problem, they lack a strong theoretical guarantee and it is still an open question whether an optimal selection strategy exists. Our work contributes in two ways. First, we show that within a Bayesian framework, the optimal selection strategy can be defined based on the posterior probability of the observed passing states between solutions and tests. The problem of identifying the best solution is then framed as an integer programming problem. Second, we propose an efficient approach for approximating this optimal (yet uncomputable) strategy, where the approximation error is bounded by the correctness of prior knowledge. We then incorporate effective prior knowledge to tailor code generation tasks. Both theoretical and empirical studies confirm that existing heuristics are limited in selecting the best solutions with plausible test cases. Our proposed approximated optimal strategy B4 significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios. Our code is publicly available at https://github.com/ZJU-CTAG/B4.

As part of a broader look at the impact of generative AI, this study investigated the emotional responses of journalists to the release of ChatGPT at the time of its launch. By analyzing nearly 1 million Tweets from journalists at major U.S. news outlets, we tracked changes in emotional tone and sentiment before and after the introduction of ChatGPT in November 2022. Using various computational and natural language processing techniques to measure emotional shifts in response to ChatGPT's release, we found an increase in positive emotion and a more favorable tone post-launch, suggesting initial optimism toward AI's potential. This research underscores the pivotal role of journalists as interpreters of technological innovation and disruption, highlighting how their emotional reactions may shape public narratives around emerging technologies. The study contributes to understanding the intersection of journalism, emotion, and AI, offering insights into the broader societal impact of generative AI tools.

Programs implemented in various programming languages form the foundation of software applications. To alleviate the burden of program migration and facilitate the development of software systems, automated program translation across languages has garnered significant attention. Previous approaches primarily focus on pairwise translation paradigms, learning translation between pairs of languages using bilingual parallel data. However, parallel data is difficult to collect for some language pairs, and the distribution of program semantics across languages can shift, posing challenges for pairwise program translation. In this paper, we argue that jointly learning a unified model to translate code across multiple programming languages is superior to separately learning from bilingual parallel data. We propose Variational Interaction for Multilingual Program Translation~(VIM-PT), a disentanglement-based generative approach that jointly trains a unified model for multilingual program translation across multiple languages. VIM-PT disentangles code into language-shared and language-specific features, using variational inference and interaction information with a novel lower bound, then achieves program translation through conditional generation. VIM-PT demonstrates four advantages: 1) captures language-shared information more accurately from various implementations and improves the quality of multilingual program translation, 2) mines and leverages the capability of non-parallel data, 3) addresses the distribution shift of program semantics across languages, 4) and serves as a unified model, reducing deployment complexity.

Generating user intent from a sequence of user interface (UI) actions is a core challenge in comprehensive UI understanding. Recent advancements in multimodal large language models (MLLMs) have led to substantial progress in this area, but their demands for extensive model parameters, computing power, and high latency makes them impractical for scenarios requiring lightweight, on-device solutions with low latency or heightened privacy. Additionally, the lack of high-quality datasets has hindered the development of such lightweight models. To address these challenges, we propose UI-JEPA, a novel framework that employs masking strategies to learn abstract UI embeddings from unlabeled data through self-supervised learning, combined with an LLM decoder fine-tuned for user intent prediction. We also introduce two new UI-grounded multimodal datasets, "Intent in the Wild" (IIW) and "Intent in the Tame" (IIT), designed for few-shot and zero-shot UI understanding tasks. IIW consists of 1.7K videos across 219 intent categories, while IIT contains 914 videos across 10 categories. We establish the first baselines for these datasets, showing that representations learned using a JEPA-style objective, combined with an LLM decoder, can achieve user intent predictions that match the performance of state-of-the-art large MLLMs, but with significantly reduced annotation and deployment resources. Measured by intent similarity scores, UI-JEPA outperforms GPT-4 Turbo and Claude 3.5 Sonnet by 10.0% and 7.2% respectively, averaged across two datasets. Notably, UI-JEPA accomplishes the performance with a 50.5x reduction in computational cost and a 6.6x improvement in latency in the IIW dataset. These results underscore the effectiveness of UI-JEPA, highlighting its potential for lightweight, high-performance UI understanding.

Visual Question-Answering (VQA) has become a key use-case in several applications to aid user experience, particularly after Vision-Language Models (VLMs) achieving good results in zero-shot inference. But evaluating different VLMs for an application requirement using a standardized framework in practical settings is still challenging. This paper introduces a comprehensive framework for evaluating VLMs tailored to VQA tasks in practical settings. We present a novel dataset derived from established VQA benchmarks, annotated with task types, application domains, and knowledge types, three key practical aspects on which tasks can vary. We also introduce GoEval, a multimodal evaluation metric developed using GPT-4o, achieving a correlation factor of 56.71% with human judgments. Our experiments with ten state-of-the-art VLMs reveals that no single model excelling universally, making appropriate selection a key design decision. Proprietary models such as Gemini-1.5-Pro and GPT-4o-mini generally outperform others, though open-source models like InternVL-2-8B and CogVLM-2-Llama-3-19B demonstrate competitive strengths in specific contexts, while providing additional advantages. This study guides the selection of VLMs based on specific task requirements and resource constraints, and can also be extended to other vision-language tasks.

Large Language Models (LLMs) have shown remarkable capabilities in processing various data structures, including graphs. While previous research has focused on developing textual encoding methods for graph representation, the emergence of multimodal LLMs presents a new frontier for graph comprehension. These advanced models, capable of processing both text and images, offer potential improvements in graph understanding by incorporating visual representations alongside traditional textual data. This study investigates the impact of graph visualisations on LLM performance across a range of benchmark tasks at node, edge, and graph levels. Our experiments compare the effectiveness of multimodal approaches against purely textual graph representations. The results provide valuable insights into both the potential and limitations of leveraging visual graph modalities to enhance LLMs' graph structure comprehension abilities.

We present the SynSUM benchmark, a synthetic dataset linking unstructured clinical notes to structured background variables. The dataset consists of 10,000 artificial patient records containing tabular variables (like symptoms, diagnoses and underlying conditions) and related notes describing the fictional patient encounter in the domain of respiratory diseases. The tabular portion of the data is generated through a Bayesian network, where both the causal structure between the variables and the conditional probabilities are proposed by an expert based on domain knowledge. We then prompt a large language model (GPT-4o) to generate a clinical note related to this patient encounter, describing the patient symptoms and additional context. The SynSUM dataset is primarily designed to facilitate research on clinical information extraction in the presence of tabular background variables, which can be linked through domain knowledge to concepts of interest to be extracted from the text - the symptoms, in the case of SynSUM. Secondary uses include research on the automation of clinical reasoning over both tabular data and text, causal effect estimation in the presence of tabular and/or textual confounders, and multi-modal synthetic data generation. The dataset can be downloaded from https://github.com/prabaey/SynSUM.

Recent advancements in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks. However, these benchmarks may not fully capture a model's code understanding abilities. We introduce CodeJudge-Eval (CJ-Eval), a novel benchmark designed to assess LLMs' code understanding abilities from the perspective of code judging rather than code generation. CJ-Eval challenges models to determine the correctness of provided code solutions, encompassing various error types and compilation issues. By leveraging a diverse set of problems and a fine-grained judging system, CJ-Eval addresses the limitations of traditional benchmarks, including the potential memorization of solutions. Evaluation of 12 well-known LLMs on CJ-Eval reveals that even state-of-the-art models struggle, highlighting the benchmark's ability to probe deeper into models' code understanding abilities. Our codes and benchmark are available at \url{https://github.com/CodeLLM-Research/CodeJudge-Eval}.

The safety of Large Language Models (LLMs) remains a critical concern due to a lack of adequate benchmarks for systematically evaluating their ability to resist generating harmful content. Previous efforts towards automated red teaming involve static or templated sets of illicit requests and adversarial prompts which have limited utility given jailbreak attacks' evolving and composable nature. We propose a novel dynamic benchmark of composable jailbreak attacks to move beyond static datasets and taxonomies of attacks and harms. Our approach consists of three components collectively called h4rm3l: (1) a domain-specific language that formally expresses jailbreak attacks as compositions of parameterized prompt transformation primitives, (2) bandit-based few-shot program synthesis algorithms that generate novel attacks optimized to penetrate the safety filters of a target black box LLM, and (3) open-source automated red-teaming software employing the previous two components. We use h4rm3l to generate a dataset of 2656 successful novel jailbreak attacks targeting 6 state-of-the-art (SOTA) open-source and proprietary LLMs. Several of our synthesized attacks are more effective than previously reported ones, with Attack Success Rates exceeding 90% on SOTA closed language models such as claude-3-haiku and GPT4-o. By generating datasets of jailbreak attacks in a unified formal representation, h4rm3l enables reproducible benchmarking and automated red-teaming, contributes to understanding LLM safety limitations, and supports the development of robust defenses in an increasingly LLM-integrated world. Warning: This paper and related research artifacts contain offensive and potentially disturbing prompts and model-generated content.

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spoken. Our approach utilizes WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context. These representations are then fed into an LLM fine-tuned using LoRA, enabling the capabilities for speech comprehension and transcription. Comprehensive experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios, highlighting the potential of LLM to handle speech-related tasks based on user instructions in such complex settings.