S\'ami, an indigenous language group comprising multiple languages, faces digital marginalization due to the limited availability of data and sophisticated language models designed for its linguistic intricacies. This work focuses on increasing technological participation for the S\'ami language. We draw the attention of the ML community towards the language modeling problem of Ultra Low Resource (ULR) languages. ULR languages are those for which the amount of available textual resources is very low, and the speaker count for them is also very low. ULRLs are also not supported by mainstream Large Language Models (LLMs) like ChatGPT, due to which gathering artificial training data for them becomes even more challenging. Mainstream AI foundational model development has given less attention to this category of languages. Generally, these languages have very few speakers, making it hard to find them. However, it is important to develop foundational models for these ULR languages to promote inclusion and the tangible abilities and impact of LLMs. To this end, we have compiled the available S\'ami language resources from the web to create a clean dataset for training language models. In order to study the behavior of modern LLM models with ULR languages (S\'ami), we have experimented with different kinds of LLMs, mainly at the order of $\sim$ seven billion parameters. We have also explored the effect of multilingual LLM training for ULRLs. We found that the decoder-only models under a sequential multilingual training scenario perform better than joint multilingual training, whereas multilingual training with high semantic overlap, in general, performs better than training from scratch.This is the first study on the S\'ami language for adapting non-statistical language models that use the latest developments in the field of natural language processing (NLP).
Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization scheme, KV-Runahead to accelerate the prompt phase. The key observation is that the extension phase generates tokens faster than the prompt phase because of key-value cache (KV-cache). Hence, KV-Runahead parallelizes the prompt phase by orchestrating multiple processes to populate the KV-cache and minimizes the time-to-first-token (TTFT). Dual-purposing the KV-cache scheme has two main benefits. First, since KV-cache is designed to leverage the causal attention map, we minimize computation and computation automatically. Second, since it already exists for the extension phase, KV-Runahead is easy to implement. We further propose context-level load-balancing to handle uneven KV-cache generation (due to the causal attention) and to optimize TTFT. Compared with an existing parallelization scheme such as tensor or sequential parallelization where keys and values are locally generated and exchanged via all-gather collectives, our experimental results demonstrate that KV-Runahead can offer over 1.4x and 1.6x speedups for Llama 7B and Falcon 7B respectively.
In recommender systems, the presentation of explanations plays a crucial role in supporting users' decision-making processes. Although numerous existing studies have focused on the effects (transparency or persuasiveness) of explanation content, explanation expression is largely overlooked. Tone, such as formal and humorous, is directly linked to expressiveness and is an important element in human communication. However, studies on the impact of tone on explanations within the context of recommender systems are insufficient. Therefore, this study investigates the effect of explanation tones through an online user study from three aspects: perceived effects, domain differences, and user attributes. We create a dataset using a large language model to generate fictional items and explanations with various tones in the domain of movies, hotels, and home products. Collected data analysis reveals different perceived effects of tones depending on the domains. Moreover, user attributes such as age and personality traits are found to influence the impact of tone. This research underscores the critical role of tones in explanations within recommender systems, suggesting that attention to tone can enhance user experience.
Large language models (LLMs) have demonstrated astonishing capabilities in natural language processing (NLP) tasks, sparking interest in their application to professional domains with higher specialized requirements. However, restricted access to closed-source LLMs via APIs and the difficulty in collecting massive high-quality datasets pose obstacles to the development of large language models in education fields of various courses. Given these challenges, we propose CourseGPT-zh, a course-oriented education LLM that supports customization and low-cost deployment. To address the comprehensiveness and diversity requirements of course-specific corpora, we design a high-quality question-answering corpus distillation framework incorporating prompt optimization, which effectively mines textbook knowledge and enhances its diversity. Moreover, considering the alignment of LLM responses with user needs, a novel method for discrete prompt optimization based on LLM-as-Judge is introduced. During optimization, this framework leverages the LLM's ability to reflect on and exploit error feedback and patterns, allowing for prompts that meet user needs and preferences while saving response length. Lastly, we obtain CourseGPT-zh based on the open-source LLM using parameter-efficient fine-tuning. Experimental results show that our discrete prompt optimization framework effectively improves the response quality of ChatGPT, and CourseGPT-zh exhibits strong professional capabilities in specialized knowledge question-answering, significantly outperforming comparable open-source models.
Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, improve response generation. Additionally, we experiment with a large language model, ChatGPT, to take advantage of the improved retrieval performance to further improve the generation results. Experimental results on two datasets show that our approach can increase retrieval and generation performance. The results also indicate that ChatGPT is a better response generator for knowledge-grounded dialogue when relevant knowledge is provided.
Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this end, we redefine the cloth manipulation problem as a partially observable Markov decision process. A supervised pre-training stage is employed to train a baseline model of our policy. In the second stage, the Proximal Policy Optimization (PPO) is utilized to guide the supervised model within the observation-aligned action space. By optimizing and updating the strategy, our proposed method increases the garment's surface area for cloth unfolding under the soft-body manipulation task. Experimental results show that our proposed framework can further improve the unfolding performance of other state-of-the-art methods.
The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited by malicious actors. We introduce a novel threat model where adversarial third-party apps manipulate the context of interaction to trick LLM-based agents into revealing private information not relevant to the task at hand. Grounded in the framework of contextual integrity, we introduce AirGapAgent, a privacy-conscious agent designed to prevent unintended data leakage by restricting the agent's access to only the data necessary for a specific task. Extensive experiments using Gemini, GPT, and Mistral models as agents validate our approach's effectiveness in mitigating this form of context hijacking while maintaining core agent functionality. For example, we show that a single-query context hijacking attack on a Gemini Ultra agent reduces its ability to protect user data from 94% to 45%, while an AirGapAgent achieves 97% protection, rendering the same attack ineffective.
Recent studies indicate that leveraging off-the-shelf or fine-tuned retrievers, capable of retrieving relevant in-context examples tailored to the input query, enhances few-shot in-context learning of English. However, adapting these methods to other languages, especially low-resource ones, poses challenges due to the scarcity of cross-lingual retrievers and annotated data. Thus, we introduce XAMPLER: Cross-Lingual Example Retrieval, a method tailored to tackle the challenge of cross-lingual in-context learning using only annotated English data. XAMPLER first trains a retriever based on Glot500, a multilingual small language model, using positive and negative English examples constructed from the predictions of a multilingual large language model, i.e., MaLA500. Leveraging the cross-lingual capacity of the retriever, it can directly retrieve English examples as few-shot examples for in-context learning of target languages. Experiments on the multilingual text classification benchmark SIB200 with 176 languages show that XAMPLER substantially improves the in-context learning performance across languages. Our code is available at \url{https://github.com/cisnlp/XAMPLER}.
Given the increasing demand for mental health assistance, artificial intelligence (AI), particularly large language models (LLMs), may be valuable for integration into automated clinical support systems. In this work, we leverage a decision transformer architecture for topic recommendation in counseling conversations between patients and mental health professionals. The architecture is utilized for offline reinforcement learning, and we extract states (dialogue turn embeddings), actions (conversation topics), and rewards (scores measuring the alignment between patient and therapist) from previous turns within a conversation to train a decision transformer model. We demonstrate an improvement over baseline reinforcement learning methods, and propose a novel system of utilizing our model's output as synthetic labels for fine-tuning a large language model for the same task. Although our implementation based on LLaMA-2 7B has mixed results, future work can undoubtedly build on the design.
Text-to-image person re-identification (ReID) retrieves pedestrian images according to textual descriptions. Manually annotating textual descriptions is time-consuming, restricting the scale of existing datasets and therefore the generalization ability of ReID models. As a result, we study the transferable text-to-image ReID problem, where we train a model on our proposed large-scale database and directly deploy it to various datasets for evaluation. We obtain substantial training data via Multi-modal Large Language Models (MLLMs). Moreover, we identify and address two key challenges in utilizing the obtained textual descriptions. First, an MLLM tends to generate descriptions with similar structures, causing the model to overfit specific sentence patterns. Thus, we propose a novel method that uses MLLMs to caption images according to various templates. These templates are obtained using a multi-turn dialogue with a Large Language Model (LLM). Therefore, we can build a large-scale dataset with diverse textual descriptions. Second, an MLLM may produce incorrect descriptions. Hence, we introduce a novel method that automatically identifies words in a description that do not correspond with the image. This method is based on the similarity between one text and all patch token embeddings in the image. Then, we mask these words with a larger probability in the subsequent training epoch, alleviating the impact of noisy textual descriptions. The experimental results demonstrate that our methods significantly boost the direct transfer text-to-image ReID performance. Benefiting from the pre-trained model weights, we also achieve state-of-the-art performance in the traditional evaluation settings.
Table summarization is a crucial task aimed at condensing information from tabular data into concise and comprehensible textual summaries. However, existing approaches often fall short of adequately meeting users' information and quality requirements and tend to overlook the complexities of real-world queries. In this paper, we propose a novel method to address these limitations by introducing query-focused multi-table summarization. Our approach, which comprises a table serialization module, a summarization controller, and a large language model (LLM), utilizes textual queries and multiple tables to generate query-dependent table summaries tailored to users' information needs. To facilitate research in this area, we present a comprehensive dataset specifically tailored for this task, consisting of 4909 query-summary pairs, each associated with multiple tables. Through extensive experiments using our curated dataset, we demonstrate the effectiveness of our proposed method compared to baseline approaches. Our findings offer insights into the challenges of complex table reasoning for precise summarization, contributing to the advancement of research in query-focused multi-table summarization.
Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution procedures-with the intuition that it is possible to in-context teach an LLM an algorithm for solving the problem. This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain, and examines the performance of two state-of-the-art LLMs across two axes: generality of examples given in prompt, and complexity of problems queried with each prompt. While our problems are very simple, we only find meaningful performance improvements from chain of thought prompts when those prompts are exceedingly specific to their problem class, and that those improvements quickly deteriorate as the size n of the query-specified stack grows past the size of stacks shown in the examples. We also create scalable variants of three domains commonly studied in previous CoT papers and demonstrate the existence of similar failure modes. Our results hint that, contrary to previous claims in the literature, CoT's performance improvements do not stem from the model learning general algorithmic procedures via demonstrations but depend on carefully engineering highly problem specific prompts. This spotlights drawbacks of chain of thought, especially the sharp tradeoff between possible performance gains and the amount of human labor necessary to generate examples with correct reasoning traces.
In this technical report, we introduce SEED-Data-Edit: a unique hybrid dataset for instruction-guided image editing, which aims to facilitate image manipulation using open-form language. SEED-Data-Edit is composed of three distinct types of data: (1) High-quality editing data produced by an automated pipeline, ensuring a substantial volume of diverse image editing pairs. (2) Real-world scenario data collected from the internet, which captures the intricacies of user intentions for promoting the practical application of image editing in the real world. (3) High-precision multi-turn editing data annotated by humans, which involves multiple rounds of edits for simulating iterative editing processes. The combination of these diverse data sources makes SEED-Data-Edit a comprehensive and versatile dataset for training language-guided image editing model. We fine-tune a pretrained Multimodal Large Language Model (MLLM) that unifies comprehension and generation with SEED-Data-Edit. The instruction tuned model demonstrates promising results, indicating the potential and effectiveness of SEED-Data-Edit in advancing the field of instructional image editing. The datasets are released in https://huggingface.co/datasets/AILab-CVC/SEED-Data-Edit.
We explore the ability of large language model (LLM)-based agents to engage in subtle deception such as strategically phrasing and intentionally manipulating information to misguide and deceive other agents. This harmful behavior can be hard to detect, unlike blatant lying or unintentional hallucination. We build an adversarial testbed mimicking a legislative environment where two LLMs play opposing roles: a corporate *lobbyist* proposing amendments to bills that benefit a specific company while evading a *critic* trying to detect this deception. We use real-world legislative bills matched with potentially affected companies to ground these interactions. Our results show that LLM lobbyists initially exhibit limited deception against strong LLM critics which can be further improved through simple verbal reinforcement, significantly enhancing their deceptive capabilities, and increasing deception rates by up to 40 points. This highlights the risk of autonomous agents manipulating other agents through seemingly neutral language to attain self-serving goals.
The efficacy of an large language model (LLM) generated text detector depends substantially on the availability of sizable training data. White-box zero-shot detectors, which require no such data, are nonetheless limited by the accessibility of the source model of the LLM-generated text. In this paper, we propose an simple but effective black-box zero-shot detection approach, predicated on the observation that human-written texts typically contain more grammatical errors than LLM-generated texts. This approach entails computing the Grammar Error Correction Score (GECScore) for the given text to distinguish between human-written and LLM-generated text. Extensive experimental results show that our method outperforms current state-of-the-art (SOTA) zero-shot and supervised methods, achieving an average AUROC of 98.7% and showing strong robustness against paraphrase and adversarial perturbation attacks.
Efficient deployment of Large Language Models (LLMs) requires batching multiple requests together to improve throughput. As the batch size, context length, or model size increases, the size of the key and value (KV) cache can quickly become the main contributor to GPU memory usage and the bottleneck of inference latency. Quantization has emerged as an effective technique for KV cache compression, but existing methods still fail at very low bit widths. We observe that distinct channels of a key/value activation embedding are highly inter-dependent, and the joint entropy of multiple channels grows at a slower rate than the sum of their marginal entropies. Based on this insight, we propose Coupled Quantization (CQ), which couples multiple key/value channels together to exploit their inter-dependency and encode the activations in a more information-efficient manner. Extensive experiments reveal that CQ outperforms or is competitive with existing baselines in preserving model quality. Furthermore, we demonstrate that CQ can preserve model quality with KV cache quantized down to 1-bit.
Numerous methods have been proposed to detect, estimate, and analyze properties of people in images, including the estimation of 3D pose, shape, contact, human-object interaction, emotion, and more. Each of these methods works in isolation instead of synergistically. Here we address this problem and build a language-driven human understanding system -- ChatHuman, which combines and integrates the skills of many different methods. To do so, we finetune a Large Language Model (LLM) to select and use a wide variety of existing tools in response to user inputs. In doing so, ChatHuman is able to combine information from multiple tools to solve problems more accurately than the individual tools themselves and to leverage tool output to improve its ability to reason about humans. The novel features of ChatHuman include leveraging academic publications to guide the application of 3D human-related tools, employing a retrieval-augmented generation model to generate in-context-learning examples for handling new tools, and discriminating and integrating tool results to enhance 3D human understanding. Our experiments show that ChatHuman outperforms existing models in both tool selection accuracy and performance across multiple 3D human-related tasks. ChatHuman is a step towards consolidating diverse methods for human analysis into a single, powerful, system for 3D human reasoning.
Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items, leading to suboptimal performance and poor generalizations. Leveraging the capability of large language models to comprehend and reason about textual content presents a promising avenue for advancing recommendation systems. To achieve this, we propose an Llm-driven knowlEdge Adaptive RecommeNdation (LEARN) framework that synergizes open-world knowledge with collaborative knowledge. We address computational complexity concerns by utilizing pretrained LLMs as item encoders and freezing LLM parameters to avoid catastrophic forgetting and preserve open-world knowledge. To bridge the gap between the open-world and collaborative domains, we design a twin-tower structure supervised by the recommendation task and tailored for practical industrial application. Through experiments on the real large-scale industrial dataset and online A/B tests, we demonstrate the efficacy of our approach in industry application. We also achieve state-of-the-art performance on six Amazon Review datasets to verify the superiority of our method.
Since late 2022, generative AI has taken the world by storm, with widespread use of tools including ChatGPT, Gemini, and Claude. Generative AI and large language model (LLM) applications are transforming how individuals find and access data and knowledge. However, the intricate relationship between open data and generative AI, and the vast potential it holds for driving innovation in this field remain underexplored areas. This white paper seeks to unpack the relationship between open data and generative AI and explore possible components of a new Fourth Wave of Open Data: Is open data becoming AI ready? Is open data moving towards a data commons approach? Is generative AI making open data more conversational? Will generative AI improve open data quality and provenance? Towards this end, we provide a new Spectrum of Scenarios framework. This framework outlines a range of scenarios in which open data and generative AI could intersect and what is required from a data quality and provenance perspective to make open data ready for those specific scenarios. These scenarios include: pertaining, adaptation, inference and insight generation, data augmentation, and open-ended exploration. Through this process, we found that in order for data holders to embrace generative AI to improve open data access and develop greater insights from open data, they first must make progress around five key areas: enhance transparency and documentation, uphold quality and integrity, promote interoperability and standards, improve accessibility and useability, and address ethical considerations.
Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. Nonetheless, state-of-the-art INT4 quantization techniques only accelerate low-batch, edge LLM inference, failing to deliver performance gains in large-batch, cloud-based LLM serving. We uncover a critical issue: existing INT4 quantization methods suffer from significant runtime overhead (20-90%) when dequantizing either weights or partial sums on GPUs. To address this challenge, we introduce QoQ, a W4A8KV4 quantization algorithm with 4-bit weight, 8-bit activation, and 4-bit KV cache. QoQ stands for quattuor-octo-quattuor, which represents 4-8-4 in Latin. QoQ is implemented by the QServe inference library that achieves measured speedup. The key insight driving QServe is that the efficiency of LLM serving on GPUs is critically influenced by operations on low-throughput CUDA cores. Building upon this insight, in QoQ algorithm, we introduce progressive quantization that can allow low dequantization overhead in W4A8 GEMM. Additionally, we develop SmoothAttention to effectively mitigate the accuracy degradation incurred by 4-bit KV quantization. In the QServe system, we perform compute-aware weight reordering and take advantage of register-level parallelism to reduce dequantization latency. We also make fused attention memory-bound, harnessing the performance gain brought by KV4 quantization. As a result, QServe improves the maximum achievable serving throughput of Llama-3-8B by 1.2x on A100, 1.4x on L40S; and Qwen1.5-72B by 2.4x on A100, 3.5x on L40S, compared to TensorRT-LLM. Remarkably, QServe on L40S GPU can achieve even higher throughput than TensorRT-LLM on A100. Thus, QServe effectively reduces the dollar cost of LLM serving by 3x. Code is available at https://github.com/mit-han-lab/omniserve.