The hallucination problem in multimodal large language models (MLLMs) remains a common issue. Although image tokens occupy a majority of the input sequence of MLLMs, there is limited research to explore the relationship between image tokens and hallucinations. In this paper, we analyze the distribution of attention scores for image tokens across each layer and head of the model, revealing an intriguing and common phenomenon: most hallucinations are closely linked to the pattern of attention sinks in the self-attention matrix of image tokens, where shallow layers exhibit dense attention sinks and deeper layers show sparse attention sinks. We further analyze the attention heads of different layers and find that heads with high-density attention sink in the image part play a positive role in alleviating hallucinations. In this paper, we propose a training-free method named \textcolor{red}{\textbf{E}}nhancing \textcolor{red}{\textbf{A}}ttention \textcolor{red}{\textbf{H}}eads (EAH), an approach designed to enhance the convergence of image tokens attention sinks in the shallow layers. EAH identifies the attention head that shows the vision sink in a shallow layer and extracts its attention matrix. This attention map is then broadcast to other heads in the layer, thereby strengthening the layer to pay more attention to the image itself. With extensive experiments, EAH shows significant hallucination-mitigating performance on different MLLMs and metrics, proving its effectiveness and generality.

In the realm of Large Language Models (LLMs), prompt optimization is crucial for model performance. Although previous research has explored aspects like rephrasing prompt contexts, using various prompting techniques (like in-context learning and chain-of-thought), and ordering few-shot examples, our understanding of LLM sensitivity to prompt templates remains limited. Therefore, this paper examines the impact of different prompt templates on LLM performance. We formatted the same contexts into various human-readable templates, including plain text, Markdown, JSON, and YAML, and evaluated their impact across tasks like natural language reasoning, code generation, and translation using OpenAI's GPT models. Experiments show that GPT-3.5-turbo's performance varies by up to 40\% in a code translation task depending on the prompt template, while larger models like GPT-4 are more robust to these variations. Our analysis highlights the need to reconsider the use of fixed prompt templates, as different formats can significantly affect model performance.

The promise of human behavioral simulation--general-purpose computational agents that replicate human behavior across domains--could enable broad applications in policymaking and social science. We present a novel agent architecture that simulates the attitudes and behaviors of 1,052 real individuals--applying large language models to qualitative interviews about their lives, then measuring how well these agents replicate the attitudes and behaviors of the individuals that they represent. The generative agents replicate participants' responses on the General Social Survey 85% as accurately as participants replicate their own answers two weeks later, and perform comparably in predicting personality traits and outcomes in experimental replications. Our architecture reduces accuracy biases across racial and ideological groups compared to agents given demographic descriptions. This work provides a foundation for new tools that can help investigate individual and collective behavior.

In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules. Traditionally, the dominant retrieval method has been Embedding-Based Retrieval (EBR) using a Deep Neural Network (DNN) dual-tower structure. However, applying transformer in retrieval tasks has been the focus of recent research, though real-world industrial deployment still presents significant challenges. In this paper, we introduce KuaiFormer, a novel transformer-based retrieval framework deployed in a large-scale content recommendation system. KuaiFormer fundamentally redefines the retrieval process by shifting from conventional score estimation tasks (such as click-through rate estimate) to a transformer-driven Next Action Prediction paradigm. This shift enables more effective real-time interest acquisition and multi-interest extraction, significantly enhancing retrieval performance. KuaiFormer has been successfully integrated into Kuaishou App's short-video recommendation system since May 2024, serving over 400 million daily active users and resulting in a marked increase in average daily usage time of Kuaishou users. We provide insights into both the technical and business aspects of deploying transformer in large-scale recommendation systems, addressing practical challenges encountered during industrial implementation. Our findings offer valuable guidance for engineers and researchers aiming to leverage transformer models to optimize large-scale content recommendation systems.

The growing capabilities of large language models (LLMs) have led to their use as substitutes for human feedback for training and assessing other LLMs. These methods often rely on `constitutions', written guidelines which a critic model uses to provide feedback and improve generations. We investigate how the choice of constitution affects feedback quality by using four different constitutions to improve patient-centered communication in medical interviews. In pairwise comparisons conducted by 215 human raters, we found that detailed constitutions led to better results regarding emotive qualities. However, none of the constitutions outperformed the baseline in learning more practically-oriented skills related to information gathering and provision. Our findings indicate that while detailed constitutions should be prioritised, there are possible limitations to the effectiveness of AI feedback as a reward signal in certain areas.

Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on both programming and natural language data tend to perform well in code-oriented tasks. However, large-scale pretraining is not always feasible due to its environmental impact and project-specific generalizability issues. In this work, first we fine-tune open-source Large language models (LLM) in parameter-efficient, quantized low-rank (QLoRA) fashion on consumer-grade hardware to improve review comment generation. Recent studies demonstrate the efficacy of augmenting semantic metadata information into prompts to boost performance in other code-related tasks. To explore this in code review activities, we also prompt proprietary, closed-source LLMs augmenting the input code patch with function call graphs and code summaries. Both of our strategies improve the review comment generation performance, with function call graph augmented few-shot prompting on the GPT-3.5 model surpassing the pretrained baseline by around 90% BLEU-4 score on the CodeReviewer dataset. Moreover, few-shot prompted Gemini-1.0 Pro, QLoRA fine-tuned Code Llama and Llama 3.1 models achieve competitive results (ranging from 25% to 83% performance improvement) on this task. An additional human evaluation study further validates our experimental findings, reflecting real-world developers' perceptions of LLM-generated code review comments based on relevant qualitative metrics.

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant computational and memory overheads. The escalating computational demands of these models necessitate the development of various compression techniques to ensure their deployment on devices, particularly in resource-constrained environments. In this paper, we propose a novel compression methodology that dynamically determines the rank of each layer using a soft thresholding mechanism, which clips the singular values with a small magnitude in a differentiable form. This approach automates the decision-making process to identify the optimal degree of compression for each layer. We have successfully applied the proposed technique to attention-based architectures, including BERT for discriminative tasks and GPT2 and TinyLlama for generative tasks. Additionally, we have validated our method on Mamba, a recently proposed state-space model. Our experiments demonstrate that the proposed technique achieves a speed-up of 1.33X to 1.72X in the encoder/ decoder with a 50% reduction in total parameters.

Robot systems capable of executing tasks based on language instructions have been actively researched. It is challenging to convey uncertain information that can only be determined on-site with a single language instruction to the robot. In this study, we propose a system that includes ambiguous parts as template variables in language instructions to communicate the information to be collected and the options to be presented to the robot for predictable uncertain events. This study implements prompt generation for each robot action function based on template variables to collect information, and a feedback system for presenting and selecting options based on template variables for user-to-robot communication. The effectiveness of the proposed system was demonstrated through its application to real-life support tasks performed by the robot.

While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data. Recently, various new methods have been proposed to adapt closed LLMs to private data without leaking private information to third parties and/or the LLM provider. In this work, we analyze the privacy protection and performance of the four most recent methods for private adaptation of closed LLMs. By examining their threat models and thoroughly comparing their performance under different privacy levels according to differential privacy (DP), various LLM architectures, and multiple datasets for classification and generation tasks, we find that: (1) all the methods leak query data, i.e., the (potentially sensitive) user data that is queried at inference time, to the LLM provider, (2) three out of four methods also leak large fractions of private training data to the LLM provider while the method that protects private data requires a local open LLM, (3) all the methods exhibit lower performance compared to three private gradient-based adaptation methods for local open LLMs, and (4) the private adaptation methods for closed LLMs incur higher monetary training and query costs than running the alternative methods on local open LLMs. This yields the conclusion that, to achieve truly privacy-preserving LLM adaptations that yield high performance and more privacy at lower costs, taking into account current methods and models, one should use open LLMs.

Fine-tuning large language models (LLMs) poses significant memory challenges, as the back-propagation process demands extensive resources, especially with growing model sizes. Recent work, MeZO, addresses this issue using a zerothorder (ZO) optimization method, which reduces memory consumption by matching the usage to the inference phase. To overcome this limitation, we introduce HELENE, a novel scalable and memory-efficient optimizer that integrates annealed A-GNB gradients with a diagonal Hessian estimation and layerwise clipping, serving as a second-order pre-conditioner. This combination allows for faster and more stable convergence. Our theoretical analysis demonstrates that HELENE improves convergence rates, particularly for models with heterogeneous layer dimensions, by reducing the dependency on the total parameter space dimension. Furthermore, HELENE remains compatible with both full parameter tuning and parameter-efficient fine-tuning (PEFT), outperforming several state-of-the-art optimizers. The codes will be released after reviewing. LLMs have demonstrated remarkable capabilities across various downstream tasks. Fine-tuning these models has become the standard approach for improving task-specific performance, in which the firstorder optimizers like Stochastic Gradient Descent (SGD) (Robbins & Monro, 1951), Adam (Diederik, 2014) and AdamW (Hutter & Loshchilov, 2017) are widely used.