论文检索

Shanbao Qiao, Xuebing Liu, Seung-Hoon Na

Among the recently emerged knowledge editing methods, in-context knowledge editing (IKE) has shown respectable abilities on knowledge editing in terms of generalization and specificity. Noting the promising advantages but unexplored issues of IKE, we propose **DistillMIKE** as a novel extension of IKE, i.e., editing **distill**ation of "**M**assive” **I**n-context **K**nowledge **E**diting in large language models (LLMs), mainly consisting of two expansions; 1) *Massive in-context knowledge editing (MIKE)*, which extends IKE to a massive editing task, aiming to inject not a single edit but a set of massive edits to LLMs; To preserve specificity, our key novel extension is a “selective” retrieval augmentation, where the retrieval-augmented IKE is only applied to “in-scope” examples, whereas the unedited model without IKE is employed for “out-of-scope” ones. 2) *Editing distillation* of MIKE using low-rank adaptation (LoRA), which distills editing abilities of MIKE to parameters of LLMs in a manner of eliminating the need of lengthy in-context demonstrations, thus removing the computational overhead encountered at the inference time. Experimental results on the zsRE and CounterFact datasets demonstrate that MIKE shows the state-of-the-art perfomrances and DistilMIKE show comparable performances with MIKE. Our code is available at https://github.com/JoveReCode/DistillMIKE.git.

Runcong Zhao, Qinglin Zhu, Hainiu Xu, Jiazheng Li, Yuxiang Zhou, Yulan He, Lin Gui

Existing datasets for narrative understanding often fail to represent the complexity and uncertainty of relationships in real-life social scenarios. To address this gap, we introduce a new benchmark, Conan, designed for extracting and analysing intricate character relation graphs from detective narratives. Specifically, we designed hierarchical relationship categories and manually extracted and annotated role-oriented relationships from the perspectives of various characters, incorporating both public relationships known to most characters and secret ones known to only a few. Our experiments with advanced Large Language Models (LLMs) like GPT-3.5, GPT-4, and Llama2 reveal their limitations in inferencing complex relationships and handling longer narratives. The combination of the Conan dataset and our pipeline strategy is geared towards understanding the ability of LLMs to comprehend nuanced relational dynamics in narrative contexts.

Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby Tavor, Yedid Hoshen

该来源暂未提供摘要。

Yafu Li, Huajian Zhang, Jianhao Yan, Yongjing Yin, Yue Zhang

Recent advances have made non-autoregressive (NAT) translation comparable to autoregressive methods (AT). However, their evaluation using BLEU has been shown to weakly correlate with human annotations. Limited research compares non-autoregressive translation and autoregressive translation comprehensively, leaving uncertainty about the true proximity of NAT to AT. To address this gap, we systematically evaluate four representative NAT methods across various dimensions, including human evaluation. Our empirical results demonstrate that despite narrowing the performance gap, state-of-the-art NAT still underperforms AT under more reliable evaluation metrics. Furthermore, we discover that explicitly modeling dependencies is crucial for generating natural language and generalizing to out-of-distribution sequences.

Taichi Aida, Danushka Bollegala

Detecting temporal semantic changes of words is an important task for various NLP applications that must make time-sensitive predictions.Lexical Semantic Change Detection (SCD) task involves predicting whether a given target word, w, changes its meaning between two different text corpora, C_1 and C_2.For this purpose, we propose a supervised two-staged SCD method that uses existing Word-in-Context (WiC) datasets.In the first stage, for a target word w, we learn two sense-aware encoders that represent the meaning of w in a given sentence selected from a corpus.Next, in the second stage, we learn a sense-aware distance metric that compares the semantic representations of a target word across all of its occurrences in C_1 and C_2.Experimental results on multiple benchmark datasets for SCD show that our proposed method achieves strong performance in multiple languages.Additionally, our method achieves significant improvements on WiC benchmarks compared to a sense-aware encoder with conventional distance functions.

Xinwei Long, Jiali Zeng, Fandong Meng, Jie Zhou, Bowen Zhou

Multi-modal entity linking (MEL) is a challenging task that requires accurate prediction of entities within extensive search spaces, utilizing multi-modal contexts. Existing generative approaches struggle with the knowledge gap between visual entity information and the intrinsic parametric knowledge of LLMs. To address this knowledge gap, we introduce a novel approach called GELR, which incorporates a knowledge retriever to enhance visual entity information by leveraging external sources. Additionally, we devise a prioritization scheme that effectively handles noisy retrieval results and manages conflicts arising from the integration of external and internal knowledge. Moreover, we propose a noise-aware instruction tuning technique during training to finely adjust the model’s ability to leverage retrieved information effectively. Through extensive experiments conducted on three benchmarks, our approach showcases remarkable improvements, ranging from 3.0% to 6.5%, across all evaluation metrics compared to strong baselines. These results demonstrate the effectiveness and superiority of our proposed method in tackling the complexities of multi-modal entity linking.

Shichao Sun, Ruifeng Yuan, Ziqiang Cao, Wenjie Li, Pengfei Liu

该来源暂未提供摘要。

Manuel Lardelli, Giuseppe Attanasio, Anne Lauscher

The translation of gender-neutral person-referring terms (e.g.,the students) is often non-trivial.Translating from English into German poses an interesting case—in German, person-referring nouns are usually gender-specific, and if the gender of the referent(s) is unknown or diverse, the generic masculine (die Studenten (m.)) is commonly used. This solution, however, reduces the visibility of other genders, such as women and non-binary people. To counteract gender discrimination, a societal movement towards using gender-fair language exists (e.g., by adopting neosystems). However, gender-fair German is currently barely supported in machine translation (MT), requiring post-editing or manual translations. We address this research gap by studying gender-fair language in English-to-German MT. Concretely, we enrich a community-created gender-fair language dictionary and sample multi-sentence test instances from encyclopedic text and parliamentary speeches.Using these novel resources, we conduct the first benchmark study involving two commercial systems and six neural MT models for translating words in isolation and natural contexts across two domains. Our findings show that most systems produce mainly masculine forms and rarely gender-neutral variants, highlighting the need for future research. We release code and data at https://github.com/g8a9/building-bridges-gender-fair-german-mt.

Naibin Gu, Peng Fu, Xiyu Liu, Bowen Shen, Zheng Lin, Weiping Wang

Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of large-scale foundation models during the training process is excessively redundant for certain fine-tuning tasks. Secondly, as the model size increases, the growth in trainable parameters of empirically added PEFT modules becomes non-negligible and redundant, leading to inefficiency. To achieve task-specific efficient fine-tuning, we propose the Light-PEFT framework, which includes two methods: Masked Early Pruning of the Foundation Model and Multi-Granularity Early Pruning of PEFT. The Light-PEFT framework allows for the simultaneous estimation of redundant parameters in both the foundation model and PEFT modules during the early stage of training. These parameters can then be pruned for more efficient fine-tuning. We validate our approach on GLUE, SuperGLUE, QA tasks, and various models. With Light-PEFT, parameters of the foundation model can be pruned by up to over 40%, while still controlling trainable parameters to be only 25% of the original PEFT method. Compared to utilizing the PEFT method directly, Light-PEFT achieves training and inference speedup, reduces memory usage, and maintains comparable performance and the plug-and-play feature of PEFT.

Ting Xu, Haiqin Yang, Fei Zhao, Zhen Wu, Xinyu Dai

Relation triplet extraction is a fundamental task in natural language processing that aims to identify semantic relationships between entities in text. It is particularly challenging in the zero-shot setting, i.e., zero-shot relation triplet extraction (ZeroRTE), where the relation sets between training and test are disjoint. Existing methods deal with this task by integrating relations into prompts, which may lack sufficient understanding of the unseen relations. To address these limitations, this paper presents a novel Two-Agent Game (TAG) approach to deliberate and debate the semantics of unseen relations. TAG consists of two agents, a generator and an extractor. They iteratively interact in three key steps: attempting, criticizing, and rectifying. This enables the agents to fully debate and understand the unseen relations. Experimental results demonstrate consistent improvement over ALBERT-Large, BART, andGPT3.5, without incurring additional inference costs in all cases. Remarkably, our method outperforms strong baselines by a significant margin, achieving an impressive 6%-16% increase in F1 scores, particularly when dealingwith FewRel with five unseen relations.

Hengyuan Zhang, Yanru Wu, Dawei Li, Sak Yang, Rui Zhao, Yong Jiang, Fei Tan

Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit speciality, excelling in specific applications. However, fine-tuning with extra data, a common practice to gain speciality, often leads to catastrophic forgetting (CF) of previously acquired versatility, hindering the model’s performance across diverse tasks. In response to this challenge, we propose CoFiTune, a coarse to fine framework in an attempt to strike the balance between speciality and versatility. At the coarse-grained level, an empirical tree-search algorithm is utilized to pinpoint and update specific modules that are crucial for speciality, while keeping other parameters frozen; at the fine-grained level, a soft-masking mechanism regulates the update to the LLMs, mitigating the CF issue without harming speciality. In an overall evaluation of both speciality and versatility, CoFiTune consistently outperforms baseline methods across diverse tasks and model scales. Compared to the full-parameter SFT, CoFiTune leads to about 14% versatility improvement and marginal speciality loss on a 13B model. Lastly, based on further analysis, we provide a speculative insight into the information forwarding process in LLMs, which helps explain the effectiveness of the proposed method. The code is available at https://github.com/rattlesnakey/CoFiTune.

Panagiotis Kaliosis, John Pavlopoulos, Foivos Charalampakos, Georgios Moschovis, Ion Androutsopoulos

该来源暂未提供摘要。

Zihao Xu, Yi Liu, Gelei Deng, Yuekang Li, Stjepan Picek

Large Language Models (LLMs) have increasingly become central to generating content with potential societal impacts. Notably, these models have demonstrated capabilities for generating content that could be deemed harmful. To mitigate these risks, researchers have adopted safety training techniques to align model outputs with societal values to curb the generation of malicious content. However, the phenomenon of “jailbreaking” — where carefully crafted prompts elicit harmful responses from models — persists as a significant challenge. This research conducts a comprehensive analysis of existing studies on jailbreaking LLMs and their defense techniques. We meticulously investigate nine attack techniques and seven defense techniques applied across three distinct language models: Vicuna, LLama, and GPT-3.5 Turbo. We aim to evaluate the effectiveness of these attack and defense techniques. Our findings reveal that existing white-box attacks underperform compared to universal techniques and that including special tokens in the input significantly affects the likelihood of successful attacks. This research highlights the need to concentrate on the security facets of LLMs. Additionally, we contribute to the field by releasing our datasets and testing framework, aiming to foster further research into LLM security. We believe these contributions will facilitate the exploration of security measures within this domain.

Lei Sun, Zhengwei Tao, Youdi Li, Hiroshi Arakawa

The integration of Large Language Models (LLMs) and knowledge graphs (KGs) has achieved remarkable success in various natural language processing tasks. However, existing methodologies that integrate LLMs and KGs often navigate the task-solving process solely based on the LLM’s analysis of the question, overlooking the rich cognitive potential inherent in the vast knowledge encapsulated in KGs. To address this, we introduce Observation-Driven Agent (ODA), a novel AI agent framework tailored for tasks involving KGs. ODA incorporates KG reasoning abilities via global observation, which enhances reasoning capabilities through a cyclical paradigm of observation, action, and reflection. Confronting the exponential explosion of knowledge during observation, we innovatively design a recursive observation mechanism. Subsequently, we integrate the observed knowledge into the action and reflection modules. Through extensive experiments, ODA demonstrates state-of-the-art performance on several datasets, notably achieving accuracy improvements of 12.87% and 8.9%.

Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank

The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice questions to limit the response space. The model is then evaluated by ranking the candidate answers by the log probability of the first token prediction. However, first-tokens may not consistently reflect the final response output, due to model’s diverse response styles such as starting with “Sure” or refusing to answer. Consequently, first-token evaluation is not indicative of model behaviour when interacting with users. But by how much? We evaluate how aligned first-token evaluation is with the text output along several dimensions, namely final option choice, refusal rate, choice distribution and robustness under prompt perturbation. Our results show that the two approaches are severely misaligned on all dimensions, reaching mismatch rates over 60%. Models heavily fine-tuned on conversational or safety data are especially impacted. Crucially, models remain misaligned even when we increasingly constrain prompts, i.e., force them to start with an option letter or example template. Our findings i) underscore the importance of inspecting the text output as well and ii) caution against relying solely on first-token evaluation.

Pranjal Chitale, Jay Gala, Raj Dabre

Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). Most prior studies primarily focus on optimizing translation quality, with limited attention to understanding the specific aspects of ICL that influence the said quality. To this end, we perform the first of its kind, exhaustive study of in-context learning for machine translation (MT). We first establish that ICL is primarily example-driven and not instruction-driven. Following this, we conduct an extensive exploration of various aspects of the examples to understand their influence on downstream performance. Our analysis includes factors such as quality and quantity of demonstrations, spatial proximity, and source versus target originality. Further, we also investigate challenging scenarios involving indirectness and misalignment of examples to understand the limits of ICL. While we establish the significance of the quality of the target distribution over the source distribution of demonstrations, we further observe that perturbations sometimes act as regularizers, resulting in performance improvements. Surprisingly, ICL does not necessitate examples from the same task, and a related task with the same target distribution proves sufficient. We hope that our study acts as a guiding resource for considerations in utilizing ICL for MT. Our code is available on https://github.com/PranjalChitale/in-context-mt-analysis.

Ming Dong, Yujing Chen, Miao Zhang, Hao Sun, Tingting He

该来源暂未提供摘要。

Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba Alabi, Xiaoyu Shen, Dietrich Klakow, Marius Mosbach

In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without needing any parameter updates. Although there have been extensive studies on English in-context learning, multilingual in-context learning remains under-explored, and we lack an in-depth understanding of the role of demonstrations in this context. To address this gap, we conduct a multidimensional analysis of multilingual in-context learning, experimenting with 5 models from different model families, 9 datasets covering classification and generation tasks, and 56 typologically diverse languages. Our results reveal that the effectiveness of demonstrations varies significantly across models, tasks, and languages. We also find that strong instruction-following models including Llama 2-Chat, GPT-3.5, and GPT-4 are largely insensitive to the quality of demonstrations. Instead, a carefully crafted template often eliminates the benefits of demonstrations for some tasks and languages altogether. These findings show that the importance of demonstrations might be overestimated. Our work highlights the need for granular evaluation across multiple axes towards a better understanding of in-context learning.

Huatao Xu, Liying Han, Qirui Yang, Mo Li, Mani Srivastava

Recent developments in Large Language Models (LLMs) have demonstrated their remarkable capabilities across a range of tasks. Questions, however, persist about the nature of LLMs and their potential to integrate common-sense human knowledge when performing tasks involving information about the real physical world. This paper delves into these questions by exploring how LLMs can be extended to interact with and reason about the physical world through IoT sensors and actuators, a concept that we term “Penetrative AI”. The paper explores such an extension at two levels of LLMs’ ability to penetrate into the physical world via the processing of sensory signals. Our preliminary findings indicate that LLMs, with ChatGPT being the representative example in our exploration, have considerable and unique proficiency in employing the embedded world knowledge for interpreting IoT sensor data and reasoning over them about tasks in the physical realm. Not only this opens up new applications for LLMs beyond traditional text-based tasks, but also enables new ways of incorporating human knowledge in cyber-physical systems.

Yihong Dong, Kangcheng Luo, Xue Jiang, Zhi Jin, Ge Li

Large language models (LLMs) have showcased remarkable potential across various tasks by conditioning on prompts. However, the quality of different human-written prompts leads to substantial discrepancies in LLMs’ performance, and improving prompts usually necessitates considerable human effort and expertise. To this end, this paper proposes Prompt with Actor-Critic Editing (PACE) for LLMs to enable automatic prompt editing. Drawing inspiration from the actor-critic algorithm in reinforcement learning, PACE leverages LLMs as the dual roles of actors and critics, conceptualizing prompt as a type of policy. PACE refines prompt, taking into account the feedback from both actors performing prompt and critics criticizing response. This process helps LLMs better align prompt to a specific task, thanks to real responses and thinking from LLMs.We conduct extensive experiments on 24 instruction induction tasks and 21 big-bench tasks. Experimental results indicate that PACE elevates the relative performance of medium/low-quality human-written prompts by up to 98%, which has comparable performance to high-quality human-written prompts. Moreover, PACE also exhibits notable efficacy for prompt generation.