Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs, often generate garbled adversarial prompts with chaotic appearance. These adversarial prompts are difficult to transfer to other LLMs, hindering their performance in attacking unknown victim models. In this paper, for the first time, we delve into the semantic meaning embedded in garbled adversarial prompts and propose a novel method that "translates" them into coherent and human-readable natural language adversarial prompts. In this way, we can effectively uncover the semantic information that triggers vulnerabilities of the model and unambiguously transfer it to the victim model, without overlooking the adversarial information hidden in the garbled text, to enhance jailbreak attacks. It also offers a new approach to discovering effective designs for jailbreak prompts, advancing the understanding of jailbreak attacks. Experimental results demonstrate that our method significantly improves the success rate of jailbreak attacks against various safety-aligned LLMs and outperforms state-of-the-arts by large margins. With at most 10 queries, our method achieves an average attack success rate of 81.8% in attacking 7 commercial closed-source LLMs, including GPT and Claude-3 series, on HarmBench. Our method also achieves over 90% attack success rates against Llama-2-Chat models on AdvBench, despite their outstanding resistance to jailbreak attacks. Large language models (LLMs) have shown impressive abilities in understanding and generating human-like text. To mitigate the risk of producing illegal or unethical content, many fine-tuning methods have been proposed to obtain safety-aligned LLMs which encourage the LLMs to refuse response to potentially harmful requests (Ouyang et al., 2022; Bai et al., 2022; Korbak et al., 2023; Glaese et al., 2022). Nevertheless, some work (Shen et al., 2023; Zou et al., 2023; Perez et al., 2022; Chao et al., 2023; Liu et al., 2023; Wei et al., 2024) indicates that these models have not yet achieved perfect safety alignment. Instead, safety-aligned LLMs can be induced to respond to harmful requests through carefully designed prompts, referred to as "jailbreaking" (Wei et al., 2024). Many automatic adversarial prompt generation methods have been proposed to improve the performance of jailbreak attacks. Among them, methods appending adversarial suffix obtained by gradientbased optimization to original harmful requests, e.g., Greedy Coordinate Gradient (GCG) (Zou et al., 2023) and its variants (Sitawarin et al., 2024; Li et al., 2024), have demonstrated remarkable success in jailbreaking white-box LLMs (Mazeika et al., 2024). However, these methods often lead to garbled adversarial prompts with chaotic appearance, that can be composed of incoherent words and symbols.

Statutory law retrieval is a typical problem in legal language processing, that has various practical applications in law engineering. Modern deep learning-based retrieval methods have achieved significant results for this problem. However, retrieval systems relying on semantic and lexical correlations often exhibit limitations, particularly when handling queries that involve real-life scenarios, or use the vocabulary that is not specific to the legal domain. In this work, we focus on overcoming this weaknesses by utilizing the logical reasoning capabilities of large language models (LLMs) to identify relevant legal terms and facts related to the situation mentioned in the query. The proposed retrieval system integrates additional information from the term--based expansion and query reformulation to improve the retrieval accuracy. The experiments on COLIEE 2022 and COLIEE 2023 datasets show that extra knowledge from LLMs helps to improve the retrieval result of both lexical and semantic ranking models. The final ensemble retrieval system outperformed the highest results among all participating teams in the COLIEE 2022 and 2023 competitions.

In the study of LLMs, sycophancy represents a prevalent hallucination that poses significant challenges to these models. Specifically, LLMs often fail to adhere to original correct responses, instead blindly agreeing with users' opinions, even when those opinions are incorrect or malicious. However, research on sycophancy in visual language models (VLMs) has been scarce. In this work, we extend the exploration of sycophancy from LLMs to VLMs, introducing the MM-SY benchmark to evaluate this phenomenon. We present evaluation results from multiple representative models, addressing the gap in sycophancy research for VLMs. To mitigate sycophancy, we propose a synthetic dataset for training and employ methods based on prompts, supervised fine-tuning, and DPO. Our experiments demonstrate that these methods effectively alleviate sycophancy in VLMs. Additionally, we probe VLMs to assess the semantic impact of sycophancy and analyze the attention distribution of visual tokens. Our findings indicate that the ability to prevent sycophancy is predominantly observed in higher layers of the model. The lack of attention to image knowledge in these higher layers may contribute to sycophancy, and enhancing image attention at high layers proves beneficial in mitigating this issue.

The recently proposed ToolkenGPT tool learning paradigm demonstrates promising performance but suffers from two major issues: first, it cannot benefit from tool documentation, and second, it often makes mistakes in whether to use a tool at all. We introduce Toolken+ that mitigates the first problem by reranking top $k$ tools selected by ToolkenGPT and the second problem with a special "Reject" option such that the model will generate a vocabulary token if "Reject" is ranked first. We demonstrate the effectiveness of Toolken+ on multistep numerical reasoning and tool selection tasks.

his paper explores what kinds of questions are best served by the way generative AI (GenAI) using Large Language Models(LLMs) that aggregate and package knowledge, and when traditional curated web-sourced search results serve users better. An experiment compared product searches using ChatGPT, Google search engine, or both helped us understand more about the compelling nature of generated responses. The experiment showed GenAI can speed up some explorations and decisions. We describe how search can deepen the testing of facts, logic, and context. We show where existing and emerging knowledge paradigms can help knowledge exploration in different ways. Experimenting with searches, our probes showed the value for curated web search provides for very specific, less popularly-known knowledge. GenAI excelled at bringing together knowledge for broad, relatively well-known topics. The value of curated and aggregated knowledge for different kinds of knowledge reflected in different user goals. We developed a taxonomy to distinguishing when users are best served by these two approaches.

Large language models (LLMs) have achieved impressive results across various tasks. However, they still struggle with long-context documents. This study evaluates the performance of three leading LLMs: GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro on lengthy, complex, and opinion-varying documents concerning infrastructure projects, under both zero-shot and few-shot scenarios. Our results indicate that GPT-4o excels in zero-shot scenarios for simpler, shorter documents, while Claude 3.5 Sonnet surpasses GPT-4o in handling more complex, sentiment-fluctuating opinions. In few-shot scenarios, Claude 3.5 Sonnet outperforms overall, while GPT-4o shows greater stability as the number of demonstrations increases.

Large Language Models (LLMs), such as GPT-3 [1] and LLaMA [2], have made substantial strides in the field of Natural Language Processing (NLP), delivering state-of-the-art performance across tasks like text summarization, machine translation, and question answering. However, their considerable computational and memory requirements render them impractical for deployment on edge devices such as smartphones, wearables, and Internet of Things (IoT) devices, where low-latency and energy efficiency are critical for real-time applications. The scaling laws that govern LLM performance suggest that increasing model size and dataset volume leads to better results [3]. However, the computational complexity and resource demands associated with larger models present a significant challenge for real-time deployment on devices with limited hardware. Industries such as healthcare, finance, and customer service require domain-specific insights with minimal latency, which current LLM architectures struggle to provide due to their reliance on cloud infrastructure and specialized hardware. To address these challenges, Shakti was developed as a solution that balances high performance, efficiency, and scalability, making it well-suited for resource-constrained environments. Shakti combines several technical innovations to enhance its efficiency and performance on edge devices. One of Shakti's core innovations is the introduction of Variable Grouped Query Attention (VGQA).

AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying non-differentiable optimization, including evolutionary methods, to refine fully-trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, image quality in 3D generative adversarial networks (GANs), image generation via Latent Diffusion Models (LDM), the number of kills per life at Doom, computational accuracy or BLEU in code translation, and human appreciations in image synthesis. In some cases, this retrofitting is performed dynamically at inference time by taking into account user inputs. The advantages of AfterLearnER are its versatility (no gradient is needed), the possibility to use non-differentiable feedback including human evaluations, the limited overfitting, supported by a theoretical study and its anytime behavior. Last but not least, AfterLearnER requires only a minimal amount of feedback, i.e., a few dozens to a few hundreds of scalars, rather than the tens of thousands needed in most related published works. Compared to fine-tuning (typically using the same loss, and gradient-based optimization on a smaller but still big dataset at a fine grain), AfterLearnER uses a minimum amount of data on the real objective function without requiring differentiability.

We propose RoCoFT, a parameter-efficient fine-tuning method for large-scale language models (LMs) based on updating only a few rows and columns of the weight matrices in transformers. Through extensive experiments with medium-size LMs like BERT and RoBERTa, and larger LMs like Bloom-7B, Llama2-7B, and Llama2-13B, we show that our method gives comparable or better accuracies than state-of-art PEFT methods while also being more memory and computation-efficient. We also study the reason behind the effectiveness of our method with tools from neural tangent kernel theory. We empirically demonstrate that our kernel, constructed using a restricted set of row and column parameters, are numerically close to the full-parameter kernel and gives comparable classification performance. Ablation studies are conducted to investigate the impact of different algorithmic choices, including the selection strategy for rows and columns as well as the optimal rank for effective implementation of our method.

By leveraging massively distributed data, federated learning (FL) enables collaborative instruction tuning of large language models (LLMs) in a privacy-preserving way. While FL effectively expands the data quantity, the issue of data quality remains under-explored in the current literature on FL for LLMs. To address this gap, we propose a new framework of federated instruction tuning of LLMs with data quality control (FedDQC), which measures data quality to facilitate the subsequent filtering and hierarchical training processes. Our approach introduces an efficient metric to assess each client's instruction-response alignment (IRA), identifying potentially noisy data through single-shot inference. Low-IRA samples are potentially noisy and filtered to mitigate their negative impacts. To further utilize this IRA value, we propose a quality-aware hierarchical training paradigm, where LLM is progressively fine-tuned from high-IRA to low-IRA data, mirroring the easy-to-hard learning process. We conduct extensive experiments on 4 synthetic and a real-world dataset, and compare our method with baselines adapted from centralized setting. Results show that our method consistently and significantly improves the performance of LLMs trained on mix-quality data in FL.