The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating responses. However, due to differences in pre-training data and objectives, there is an inevitable gap between the documents ranked as relevant by the reranker and those required by the generator to support answering the query. To address this gap, we propose RADIO, a novel and practical preference alignment framework with RAtionale DIstillatiOn. Specifically, We first propose a rationale extraction method that leverages the reasoning capabilities of Large Language Models (LLMs) to extract the rationales necessary for answering the query. Subsequently, a rationale-based alignment process is designed to rerank the documents based on the extracted rationales, and fine-tune the reranker to align the preferences. We conduct extensive experiments on two tasks across three datasets to demonstrate the effectiveness of our approach compared to baseline methods. Our code is released online to ease reproduction.

Large Language Models for Code (LLMs4Code) have been found to exhibit outstanding performance in the software engineering domain, especially the remarkable performance in coding tasks. However, even the most advanced LLMs4Code can inevitably contain incorrect or outdated code knowledge. Due to the high cost of training LLMs4Code, it is impractical to re-train the models for fixing these problematic code knowledge. Model editing is a new technical field for effectively and efficiently correcting erroneous knowledge in LLMs, where various model editing techniques and benchmarks have been proposed recently. Despite that, a comprehensive study that thoroughly compares and analyzes the performance of the state-of-the-art model editing techniques for adapting the knowledge within LLMs4Code across various code-related tasks is notably absent. To bridge this gap, we perform the first systematic study on applying state-of-the-art model editing approaches to repair the inaccuracy of LLMs4Code. To that end, we introduce a benchmark named CLMEEval, which consists of two datasets, i.e., CoNaLa-Edit (CNLE) with 21K+ code generation samples and CodeSearchNet-Edit (CSNE) with 16K+ code summarization samples. With the help of CLMEEval, we evaluate six advanced model editing techniques on three LLMs4Code: CodeLlama (7B), CodeQwen1.5 (7B), and Stable-Code (3B). Our findings include that the external memorization-based GRACE approach achieves the best knowledge editing effectiveness and specificity (the editing does not influence untargeted knowledge), while generalization (whether the editing can generalize to other semantically-identical inputs) is a universal challenge for existing techniques. Furthermore, building on in-depth case analysis, we introduce an enhanced version of GRACE called A-GRACE, which incorporates contrastive learning to better capture the semantics of the inputs.

Multimodal large language models (MLLMs) have shown remarkable progress in high-level semantic tasks such as visual question answering, image captioning, and emotion recognition. However, despite advancements, there remains a lack of standardized benchmarks for evaluating MLLMs performance in multi-object sentiment analysis, a key task in semantic understanding. To address this gap, we introduce MOSABench, a novel evaluation dataset designed specifically for multi-object sentiment analysis. MOSABench includes approximately 1,000 images with multiple objects, requiring MLLMs to independently assess the sentiment of each object, thereby reflecting real-world complexities. Key innovations in MOSABench include distance-based target annotation, post-processing for evaluation to standardize outputs, and an improved scoring mechanism. Our experiments reveal notable limitations in current MLLMs: while some models, like mPLUG-owl and Qwen-VL2, demonstrate effective attention to sentiment-relevant features, others exhibit scattered focus and performance declines, especially as the spatial distance between objects increases. This research underscores the need for MLLMs to enhance accuracy in complex, multi-object sentiment analysis tasks and establishes MOSABench as a foundational tool for advancing sentiment analysis capabilities in MLLMs.

Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we explore two key questions under the new challenge of code preference learning: (i) How do we train models to predict meaningful preferences for code? and (ii) How do human and LLM preferences align with verifiable code properties and developer code tastes? Furthermore, we discover the prohibitive costs and limitations of human-based code preference: despite spending 23.4 person-minutes on each task, 15.1 40.3% of tasks remain unsolved. Compared to model-based preference, human preference tends to be more accurate under the objective of code correctness, while being sub-optimal for non-functional objectives. Large Language Models (LLMs) for code (Chen et al., 2021; GitHub, 2023; Amazon Web Services, 2023) have become instrumental in modern software development. Code LLMs assist developers in various scenarios, from suggesting code completions and generating functional code based on user instructions to proposing complex code changes to resolve bug reports and feature requests. Instruction-tuned LLMs (Luo et al., 2024; Wei et al., 2024) are increasingly adept at generating functional code based on natural language instructions. However, evaluating the quality of LLM-generated code remains challenging, particularly regarding code correctness, efficiency, security, adherence to best practices, and alignment with developer preferences. Effectively and efficiently assessing LLM-generated code against these properties is crucial for both evaluation (Liu et al., 2023b) and preference optimization for code LLMs (Weyssow et al., 2024). Nevertheless, the subject of learning code preferences has been largely under-explored, motivating us to study code preferences systematically and train code preference models with new data and modeling methods. Following the established format in LLM-as-a-judge (Chiang et al., 2024), we define the code preference task as follows: Given a user query, a pair of two candidate code responses, and optionally a preference criterion, code preference is demonstrated by choosing one response over the other. Work done during a research internship at AWS AI Labs. Code execution: Code preference in another way can be confidently determined by execution statuses (Liu et al., 2023a). However, applying code execution to arbitrary programs poses challenges due to (i) setup complexity, (ii) code incompleteness, and (iii) execution overhead.

We propose a tensor-based criterion for benign landscape in phase retrieval and establish boundedness of gradient trajectories. This implies that gradient descent will converge to a global minimum for almost every initial point.

Knowledge editing has emerged as an efficient technology for updating the knowledge of large language models (LLMs), attracting increasing attention in recent years. However, there is a lack of effective measures to prevent the malicious misuse of this technology, which could lead to harmful edits in LLMs. These malicious modifications could cause LLMs to generate toxic content, misleading users into inappropriate actions. In front of this risk, we introduce a new task, Knowledge Editing Type Identification (KETI), aimed at identifying different types of edits in LLMs, thereby providing timely alerts to users when encountering illicit edits. As part of this task, we propose KETIBench, which includes five types of harmful edits covering most popular toxic types, as well as one benign factual edit. We develop four classical classification models and three BERT-based models as baseline identifiers for both open-source and closedsource LLMs. Our experimental results, across 42 trials involving two models and three knowledge editing methods, demonstrate that all seven baseline identifiers achieve decent identification performance, highlighting the feasibility of identifying malicious edits in LLMs. Additional analyses reveal that the performance of the identifiers is independent of the reliability of the knowledge editing methods and exhibits cross-domain generalization, enabling the identification of edits from unknown sources. All data and code are available in https://github.com/xpq-tech/KETI. Warning: This paper contains examples of toxic text. Knowledge editing is an emerging technology designed to efficiently rectify errors or outdated knowledge in large language models (LLMs) (Yao et al., 2023). In recent years, it has garnered increasing attention (Wang et al., 2023).

Linear control models have gained extensive application in vehicle control due to their simplicity, ease of use, and support for stability analysis. However, these models lack adaptability to the changing environment and multi-objective settings. Reinforcement learning (RL) models, on the other hand, offer adaptability but suffer from a lack of interpretability and generalization capabilities. This paper aims to develop a family of RL-based controllers enhanced by physics-informed policies, leveraging the advantages of both physics-based models (data-efficient and interpretable) and RL methods (flexible to multiple objectives and fast computing). We propose the Physics-Enhanced Residual Policy Learning (PERPL) framework, where the physics component provides model interpretability and stability. The learning-based Residual Policy adjusts the physics-based policy to adapt to the changing environment, thereby refining the decisions of the physics model. We apply our proposed model to decentralized control to mixed traffic platoon of Connected and Automated Vehicles (CAVs) and Human-driven Vehicles (HVs) using a constant time gap (CTG) strategy for cruising and incorporating actuator and communication delays. Experimental results demonstrate that our method achieves smaller headway errors and better oscillation dampening than linear models and RL alone in scenarios with artificially extreme conditions and real preceding vehicle trajectories. At the macroscopic level, overall traffic oscillations are also reduced as the penetration rate of CAVs employing the PERPL scheme increases.

Our study delves into Multimodal Entity Linking, aligning the mention in multimodal information with entities in knowledge base. Existing methods are still facing challenges like ambiguous entity representations and limited image information utilization. Thus, we propose dynamic entity extraction using ChatGPT, which dynamically extracts entities and enhances datasets. We also propose a method: Dynamically Integrate Multimodal information with knowledge base (DIM), employing the capability of the Large Language Model (LLM) for visual understanding. The LLM, such as BLIP-2, extracts information relevant to entities in the image, which can facilitate improved extraction of entity features and linking them with the dynamic entity representations provided by ChatGPT. The experiments demonstrate that our proposed DIM method outperforms the majority of existing methods on the three original datasets, and achieves state-of-the-art (SOTA) on the dynamically enhanced datasets (Wiki+, Rich+, Diverse+).

Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA methods use a joint prediction approach to identify aspects and sentiments simultaneously. However, we argue that joint models are not always superior. Our analysis shows that joint models struggle to align relevant text tokens with image patches, leading to misalignment and ineffective image utilization. In contrast, a pipeline framework first identifies aspects through MATE (Multimodal Aspect Term Extraction) and then aligns these aspects with image patches for sentiment classification (MASC: Multimodal Aspect-Oriented Sentiment Classification). This method is better suited for multimodal scenarios where effective image use is crucial. We present three key observations: (a) MATE and MASC have different feature requirements, with MATE focusing on token-level features and MASC on sequence-level features; (b) the aspect identified by MATE is crucial for effective image utilization; and (c) images play a trivial role in previous MABSA methods due to high noise. Based on these observations, we propose a pipeline framework that first predicts the aspect and then uses translation-based alignment (TBA) to enhance multimodal semantic consistency for better image utilization. Our method achieves state-of-the-art (SOTA) performance on widely used MABSA datasets Twitter-15 and Twitter-17. This demonstrates the effectiveness of the pipeline approach and its potential to provide valuable insights for future MABSA research. For reproducibility, the code and checkpoint will be released.

In the domain of code generation, self-debugging is crucial. It allows LLMs to refine their generated code based on execution feedback. This is particularly important because generating correct solutions in one attempt proves challenging for complex tasks. Prior works on self-debugging mostly focus on prompting methods by providing LLMs with few-shot examples, which work poorly on small open-sourced LLMs. In this work, we propose a training framework that significantly improves self-debugging capability of LLMs. Intuitively, we observe that a chain of explanations on the wrong code followed by code refinement helps LLMs better analyze the wrong code and do refinement. We thus propose an automated pipeline to collect a high-quality dataset for code explanation and refinement by generating a number of explanations and refinement trajectories and filtering via execution verification. We perform supervised fine-tuning (SFT) and further reinforcement learning (RL) on both success and failure trajectories with a novel reward design considering code explanation and refinement quality. SFT improves the pass@1 by up to 15.92% and pass@10 by 9.30% over four benchmarks. RL training brings additional up to 3.54% improvement on pass@1 and 2.55% improvement on pass@10. The trained LLMs show iterative refinement ability, and can keep refining code continuously. Lastly, our human evaluation shows that the LLMs trained with our framework generate more useful code explanations and help developers better understand bugs in source code.