论文检索

Weize Chen, Chenfei Yuan, Jiarui Yuan, Yusheng Su, Chen Qian, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun

Natural language (NL) has long been the predominant format for human cognition and communication, and by extension, has been similarly pivotal in the development and application of Large Language Models (LLMs). Yet, besides NL, LLMs have seen various non-NL formats during pre-training, such as code and logical expression. NL’s status as the optimal format for LLMs, particularly in single-LLM reasoning and multi-agent communication, has not been thoroughly examined. In this work, we challenge the default use of NL by exploring the utility of non-NL formats in these contexts. We show that allowing LLMs to autonomously select the most suitable format before reasoning or communicating leads to a 3.3 to 5.7% improvement in reasoning efficiency for different LLMs, and up to a 72.7% reduction in token usage in multi-agent communication, all while maintaining communicative effectiveness. Our comprehensive analysis further reveals that LLMs can devise a format from limited task instructions and that the devised format is effectively transferable across different LLMs. Intriguingly, the structured communication format decided by LLMs exhibits notable parallels with established agent communication languages, suggesting a natural evolution towards efficient, structured communication in agent communication. Our code will be released to facilitate further exploration.

Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi, Kevin Small

Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users’ contextual search intent when generating responses is an understudied topic for conversational question answering (QA). This conversational extension leads to additional concerns when compared to single-turn QA as it is more challenging for systems to comprehend conversational context and manage retrieved passages over multiple turns. In this work, we propose a method for enabling LLMs to decide when to retrieve in RAG settings given a conversational context. When retrieval is deemed necessary, the LLM then rewrites the conversation for passage retrieval and judges the relevance of returned passages before response generation. Operationally, we build on the single-turn SELF-RAG framework (Asai et al., 2023) and propose SELF-multi-RAG for conversational settings. SELF-multi-RAG demonstrates improved capabilities over single-turn variants with respect to retrieving relevant passages (by using summarized conversational context) and assessing the quality of generated responses. Experiments on three conversational QA datasets validate the enhanced response generation capabilities of SELF-multi-RAG with improvements of ~13% measured by human annotation.

Sheng Zhang, Hui Li, Rongrong Ji

Code pre-trained language models (CPLMs) have received great attention since they can benefit various tasks that facilitate software development and maintenance. However, CPLMs are trained on massive open-source code, raising concerns about potential data infringement. This paper launches the study of detecting unauthorized code use in CPLMs, i.e., Code Membership Inference (CMI) task. We design a framework Buzzer for different settings of CMI. Buzzer deploys several inference techniques, including signal extraction from pre-training tasks, hard-to-learn sample calibration and weighted inference, to identify code membership status accurately. Extensive experiments show that CMI can be achieved with high accuracy using Buzzer. Hence, Buzzer can serve as a CMI tool and help protect intellectual property rights. The implementation of Buzzer is available at: https://github.com/KDEGroup/Buzzer

Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference data. Conventional RMs are trained on pairwise responses to the same user request, with relative ratings indicating which response humans prefer. The trained RM serves as a proxy for human preferences. However, due to the black-box nature of RMs, their outputs lack interpretability, as humans cannot intuitively understand why an RM thinks a response is good or not. As RMs act as human preference proxies, it is desirable for them to be human-interpretable to ensure that their internal decision processes are consistent with human preferences and to prevent reward hacking in LLM alignment. To build RMs with interpretable preferences, we propose a two-stage approach: i) train an Absolute-Rating Multi-Objective Reward Model (ArmoRM) with multi-dimensional absolute-rating data, each dimension corresponding to a human-interpretable objective (e.g., honesty, verbosity, safety); ii) employ a Mixture-of-Experts (MoE) strategy with a gating network that automatically selects the most suitable reward objectives based on the context. We efficiently trained an ArmoRM with Llama-3 8B and a gating network consisting of a shallow MLP on top of the ArmoRM. Our trained model, ArmoRM-Llama3-8B, obtains state-of-the-art performance on RewardBench, a benchmark evaluating RMs for language modeling. Notably, the performance of our model surpasses the LLM-as-a-judge method with GPT-4 judges by a margin, and approaches the performance of the much larger Nemotron-4 340B reward model.

Yusheng Liao, Shuyang Jiang, Zhe Chen, Yu Wang, Yanfeng Wang

Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowledge-intensive tasks and alignment-required tasks. Previous approaches either ignore the latter task or focus on a minority of tasks and hence lose generalization. To address these drawbacks, we propose a progressive fine-tuning pipeline. This pipeline employs a and a to encode diverse knowledge in the first stage and filter out detrimental information. In the second stage, we drop the to avoid the interference of suboptimal representation and leverage an additional alignment module optimized towards an orthogonal direction to the knowledge space to mitigate knowledge forgetting. Based on this two-stage paradigm, we proposed a Medical LLM through decoupling Clinical Alignment and Knowledge Aggregation (), which is designed to achieve promising performance on over 20 medical tasks, as well as results on specific medical alignment tasks. Various model sizes of (1.8B, 7B, 14B) all demonstrate significant improvements over existing models with similar model sizes. Our code and datasets are available at https://github.com/BlueZeros/MedCare.

Clement Christophe, Tathagata Raha, Svetlana Maslenkova, Muhammad Umar Salman, Praveenkumar Kanithi, Marco AF Pimentel, Shadab Khan

Large Language Models (LLMs) have demonstrated significant potential in revolutionizing clinical applications. In this study, we investigate the efficacy of four techniques in adapting LLMs for clinical use-cases: continuous pretraining, instruct fine-tuning, NEFTune, and prompt engineering. We employ these methods on Mistral 7B and Mixtral 8x7B models, leveraging a large-scale clinical pretraining dataset of 50 billion tokens and an instruct fine-tuning dataset of 500 million tokens. Our evaluation across various clinical tasks reveals nuanced insights. While continuous pretraining beyond 250 billion tokens yields marginal improvements, instruct fine-tuning emerges as a more influential factor. Notably, NEFTune, designed primarily to enhance generation quality, surprisingly demonstrates additional gains on our benchmark. These findings underscore the importance of tailoring fine-tuning strategies and exploring innovative techniques to optimize LLM performance in the clinical domain.

Karmvir Singh Phogat, Sai Akhil Puranam, Sridhar Dasaratha, Chetan Harsha, Shashishekar Ramakrishna

Recent research has shown that smaller language models can acquire substantial reasoning abilities when fine-tuned with reasoning exemplars crafted by a significantly larger teacher model. We explore this paradigm for the financial domain, focusing on the challenge of answering questions that require multi-hop numerical reasoning over financial texts. We assess the performance of several smaller models that have been fine-tuned to generate programs that encode the required financial reasoning and calculations. Our findings demonstrate that these fine-tuned smaller models approach the performance of the teacher model.To provide a granular analysis of model performance, we propose an approach to investigate the specific student model capabilities that are enhanced by fine-tuning. Our empirical analysis indicates that fine-tuning refines the student models ability to express and apply the required financial concepts along with adapting the entity extraction for the specific data format. In addition, we hypothesize and demonstrate that comparable financial reasoning capability can be induced using relatively smaller datasets.

Jongho Kim, Romain Storaï, Seung-won Hwang

In this study, we investigate the potential of language models (LMs) in aiding patients experiencing anomia, a difficulty identifying the names of items. Identifying the intended target item from patient’s circumlocution involves the two challenges of term failure and error. (1) The terms relevant to identifying the item remain unseen. (2) What makes the challenge unique is inherent perturbed terms by semantic paraphasia, which are not exactly related to the target item, hindering the identification process. To address each, we propose robustifying the model from semantically paraphasic errors and enhancing the model with unseen terms with gradient-based selective augmentation (GradSelect). Specifically, the gradient value controls augmented data quality amid semantic errors, while the gradient variance guides the inclusion of unseen but relevant terms. Due to limited domain-specific datasets, we evaluate the model on the Tip of the Tongue dataset as an intermediary task and then apply our findings to real patient data from AphasiaBank. Our results demonstrate strong performance against baselines, aiding anomia patients by addressing the outlined challenges.

Zhu JianHao, Changze Lv, Xiaohua Wang, Muling Wu, Wenhao Liu, Tianlong Li, Zixuan Ling, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

Conventional federated learning primarily aims to secure the privacy of data distributed across multiple edge devices, with the global model dispatched to edge devices for parameter updates during the learning process. However, the development of large language models (LLMs) requires substantial data and computational resources, rendering them valuable intellectual properties for their developers and owners. To establish a mechanism that protects both data and model privacy in a federated learning context, we introduce a method that just needs to distribute a quantized version of the model’s parameters during training. This method enables accurate gradient estimations for parameter updates while preventing clients from accessing a model whose performance is comparable to the centrally hosted one. Moreover, we combine this quantization strategy with LoRA, a popular and parameter-efficient fine-tuning method, to significantly reduce communication costs in federated learning. The proposed framework, named FedLPP, successfully ensures both data and model privacy in the federated learning context. Additionally, the learned central model exhibits good generalization and can be trained in a resource-efficient manner.

Atula Tejaswi, Nilesh Gupta, Eunsol Choi

Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We conduct systematic experiments on how design choices (base model selection, vocabulary extension, and continued pretraining) impact the adapted LLM, both in terms of efficiency (how many tokens are needed to encode the same amount of information) and end task performance. We find that (1) the initial performance of LLM does not always correlate with the final performance after the adaptation. Adapting an English-centric models can yield better results than adapting multilingual models despite their worse initial performance on low-resource languages. (2) Efficiency can easily improved with simple vocabulary extension and continued pretraining in most LLMs we study, and (3) The optimal adaptation method (choice of the base model, new vocabulary size, training data, initialization strategy) is highly language-dependent, and the simplest embedding initialization works well across various experimental settings. Together, our work lays foundations on efficiently building language-specific LLMs by adapting existing LLMs.

Fengzhu Zeng, Wenqian Li, Wei Gao, Yan Pang

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap. To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions. Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even surpass GPT-4V.

Cheng Yang, Yang Sui, Jinqi Xiao, Lingyi Huang, Yu Gong, Yuanlin Duan, Wenqi Jia, Miao Yin, Yu Cheng, Bo Yuan

The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer activated parameters. Despite this efficiency, their enormous parameter size still leads to high deployment costs. In this paper, we introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. First, in the inter-expert pruning stage, we analyze the importance of each layer and propose the Layer-wise Genetic Search and Block-wise KT-Reception Field with the non-uniform pruning ratio to prune the individual expert. Second, in the intra-expert decomposition stage, we apply the low-rank decomposition to further compress the parameters within the remaining experts. Extensive experiments on Qwen1.5-MoE-A2.7B, Deepseek-V2-Lite, and Mixtral-8\times7B, demonstrate that our proposed methods can both reduce the model size and enhance inference efficiency while maintaining performance in various zero-shot tasks.

Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu

Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender-profession or race-crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the **D**ataset **o**f **r**etrieved **a**ssociations (**Dora**) publicly available.

Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang 等

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs’ responses in an aligned, customizable and explainable manner. In this paper, we propose ShieldLM, an LLM-based safety detector, which aligns with common safety standards, supports customizable detection rules, and provides explanations for its decisions. To train ShieldLM, we compile a large bilingual dataset comprising 14,387 query-response pairs, annotating the safety of responses based on various safety standards. Through extensive experiments, we demonstrate that ShieldLM surpasses strong baselines across four test sets, showcasing remarkable customizability and explainability. Besides performing well on standard detection datasets, ShieldLM has also been shown to be effective as a safety evaluator for advanced LLMs. ShieldLM is released at https://github.com/thu-coai/ShieldLM to support accurate and explainable safety detection under various safety standards.

Wanshi Xu, Xuxin Cheng, Zhihong Zhu, Zhanpeng Chen, Yuexian Zou

Due to the rapid development with pre-trained language models, fully end-to-end Task-Oriented Dialogue (TOD) systems exhibit superior performance. How to achieve the ability to efficiently retrieve entities in cross-domain large-scale databases is a key issue. Most existing end-to-end Task-Oriented Dialogue systems suffer from the following problems: The ability to handle erroneous but easily confused entities needs to be improved; Matching information between contexts and entities is not captured, leading to weak modeling of domain-invariant and interpretable features, making it difficult to generalize to unseen domains. In this paper, we propose a method for knowledge retrieval driven by matching representations. The approach consists of a matching signal extractor for extracting matching representations between contexts and entities that have generic conceptual features and hence domain invariant properties, and an Attribute Filter for filtering irrelevant information to facilitate the re-selection of entities. Experiments on three standard benchmarks at the dialogue level and on large knowledge bases show that our retriever performs knowledge retrieval more efficiently than existing approaches.

Yufei Tian, Zeyu Pan, Nanyun Peng

The increasing capability of large language models (LLMs) to generate fluent long-form texts is presenting new challenges in distinguishing these outputs from those of humans. Existing zero-shot detectors that primarily focus on token-level distributions are vulnerable to real-world domain shift including different decoding strategies, variations in prompts, and attacks. We propose a more robust method that incorporates abstract elements—such as topic or event transitions—as key deciding factors, by training a latent-space model on sequences of events or topics derived from human-written texts. On three different domains, machine generations which are originally inseparable from humans’ on the token level can be better distinguished with our latent-space model, leading to a 31% improvement over strong baselines such as DetectGPT. Our analysis further reveals that unlike humans, modern LLMs such as GPT-4 selecting event triggers and transitions differently, and inherent disparity regardless of the generation configurations adopted in real-time.

Bolei He, Nuo Chen, Xinran He, Lingyong Yan, Zhenkai Wei, Jinchang Luo, Zhen-Hua Ling

Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) by incorporating extensive knowledge retrieved from external sources. However, such approach encounters some challenges: Firstly, the original queries may not be suitable for precise retrieval, resulting in erroneous contextual knowledge; Secondly, the language model can easily generate inconsistent answer with external references due to their knowledge boundary limitation. To address these issues, we propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal generation consistency. Specifically, we integrate the verification module into the RAG, engaging in scoring, judgment, and rewriting. To correct external retrieval errors, CoV-RAG retrieves new knowledge using a revised query. To correct internal generation errors, we unify QA and verification tasks with a Chain-of-Thought (CoT) reasoning during training. Our comprehensive experiments across various LLMs demonstrate the effectiveness and adaptability compared with other strong baselines. Especially, our CoV-RAG can significantly surpass the state-of-the-art baselines using different LLM backbones.

Erica K. Shimomoto, Edison Marrese-Taylor, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao

This paper focuses on the task of open-domain live commentary generation. Compared to domain-specific work in this task, this setting proved particularly challenging due to the absence of domain-specific features. Aiming to bridge this gap, we integrate spatial information by proposing an utterance generation model with a novel spatial graph that is flexible to deal with the open-domain characteristics of the commentaries and significantly improves performance. Furthermore, we propose a novel evaluation scheme, more suitable for live commentary generation, that uses LLMs to automatically check whether generated utterances address essential aspects of the video via the answerability of questions extracted directly from the videos using LVLMs. Our results suggest that using a combination of our answerability score and a standard machine translation metric is likely a more reliable way to evaluate the performance in this task.

Yin Jou Huang, Rafik Hadfi

Psychological evidence reveals the influence of personality traits on decision-making. For instance, agreeableness is generally associated with positive outcomes in negotiations, whereas neuroticism is often linked to less favorable outcomes. This paper introduces a simulation framework centered on large language model (LLM) agents endowed with synthesized personality traits. The agents negotiate within bargaining domains and possess customizable personalities and objectives. The experimental results show that the behavioral tendencies of LLM-based simulations can reproduce behavioral patterns observed in human negotiations. The contribution is twofold. First, we propose a simulation methodology that investigates the alignment between the linguistic and economic capabilities of LLM agents. Secondly, we offer empirical insights into the strategic impacts of Big Five personality traits on the outcomes of bilateral negotiations. We also provide an in-depth analysis based on simulated bargaining dialogues to reveal intriguing behaviors, including deceitful and compromising behaviors.

Ayrton San Joaquin, Bin Wang, Zhengyuan Liu, Nicholas Asher, Brian Lim, Philippe Muller, Nancy F. Chen

Despite advancements, fine-tuning Large Language Models (LLMs) remains costly due to the extensive parameter count and substantial data requirements for model generalization. Accessibility to computing resources remains a barrier for the open-source community. To address this challenge, we propose the In2Core algorithm, which selects a coreset by analyzing the correlation between training and evaluation samples with a trained model. Notably, we assess the model’s internal gradients to estimate this relationship, aiming to rank the contribution of each training point. To enhance efficiency, we propose an optimization to compute influence functions with a reduced number of layers while achieving similar accuracy. By applying our algorithm to instruction fine-tuning data of LLMs, we can achieve similar performance with just 50% of the training data. Meantime, using influence functions to analyze model coverage to certain testing samples could provide a reliable and interpretable signal on the training set’s coverage of those test points.