论文检索

Jungseob Lee, Hyeonseok Moon, Seungjun Lee, Chanjun Park, Sugyeong Eo, Hyunwoong Ko, Jaehyung Seo, Seungyoon Lee, Heuiseok Lim

Byte Pair Encoding is an effective approach in machine translation across several languages. However, our analysis indicates that BPE is prone to over-segmentation in the morphologically rich language, Korean, which can erode word semantics and lead to semantic confusion during training. This semantic confusion, stemming from over-segmentation, ultimately contributes to a degradation of overall translation quality. To address this issue, we introduce Length-aware Subword Vocabulary Construction (LeVoC), a novel approach strategically incorporating longer words into the vocabulary. By utilizing an external monolingual Korean corpus, LeVoC extracts and integrates long words, effectively preserving morphological information and reducing semantic confusion. Our experiments demonstrate that LeVoC not only significantly outperforms BPE, but also can be applied to and surpass current state-of-the-art morpheme-aware subword tokenization methods. We provide evidence that the difficulty in translating sentences with long words in Korean is associated with morphological compositionality, and LeVoC’s ability to reduce semantic confusion during training leads to improved translation quality.

Omer Goldman, Avi Caciularu, Matan Eyal, Kris Cao, Idan Szpektor, Reut Tsarfaty

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear. In this paper, we argue for the theoretical importance of compression, that can be viewed as 0-gram language modeling where equal probability is assigned to all tokens. We also demonstrate the empirical importance of compression for downstream success of pre-trained language models. We control the compression ability of several BPE tokenizers by varying the amount of documents available during their training: from 1 million documents to a character-based tokenizer equivalent to no training data at all. We then pre-train English language models based on those tokenizers and fine-tune them over several tasks. We show that there is a correlation between tokenizers’ compression and models’ downstream performance, suggesting that compression is a reliable intrinsic indicator of tokenization quality. These correlations are more pronounced for generation tasks (over classification) or for smaller models (over large ones). We replicated a representative part of our experiments on Turkish and found similar results, confirming that our results hold for languages with typological characteristics dissimilar to English. We conclude that building better compressing tokenizers is a fruitful avenue for further research and for improving overall model performance.

Tzuf Paz-Argaman, John Palowitch, Sayali Kulkarni, Reut Tsarfaty, Jason Baldridge

Similar to vision-and-language navigation (VLN) tasks that focus on bridging the gap between vision and language for embodied navigation, the new Rendezvous (RVS) task requires reasoning over allocentric spatial relationships using non-sequential navigation instructions and maps. However, performance substantially drops in new environments with no training data.Using opensource descriptions paired with coordinates (e.g., Wikipedia) provides training data but suffers from limited spatially-oriented text resulting in low geolocation resolution. We propose a large-scale augmentation method for generating high-quality synthetic data for new environments using readily available geospatial data. Our method constructs a grounded knowledge-graph, capturing entity relationships. Sampled entities and relations (“shop north of school”) generate navigation instructions via (i) generating numerous templates using context-free grammar (CFG) to embed specific entities and relations; (ii) feeding the entities and relation into a large language model (LLM) for instruction generation. A comprehensive evaluation on RVS, showed that our approach improves the 100-meter accuracy by 45.83% on unseen environments. Furthermore, we demonstrate that models trained with CFG-based augmentation achieve superior performance compared with those trained with LLM-based augmentation, both in unseen and seen environments. These findings suggest that the potential advantages of explicitly structuring spatial information for text-based geospatial reasoning in previously unknown, can unlock data-scarce scenarios.

Joe Stacey, Marek Rei

Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily generalise to out-of-distribution (OOD) settings. We investigate two complementary methods for improving the robustness of the resulting student models on OOD domains. The first approach augments the distillation with generated unlabeled examples that match the target distribution. The second method upsamples data points among the training set that are similar to the target distribution. When applied on the task of natural language inference (NLI), our experiments on MNLI show that distillation with these modifications outperforms previous robustness solutions. We also find that these methods improve performance on OOD domains even beyond the target domain.

Yuyan Chen, Yueze Li, Songzhou Yan, Sijia Liu, Jiaqing Liang, Yanghua Xiao

The evaluation of the problem-solving capability under incomplete information scenarios of Large Language Models (LLMs) is increasingly important, encompassing capabilities such as questioning, knowledge search, error detection, and path planning. Current research mainly focus on LLMs’ problem-solving capability such as “Twenty Questions”.However, these kinds of games do not require recognizing misleading cues which are necessary in the incomplete information scenario.Moreover, the existing game such as “Who is undercover” are highly subjective, making it challenging for evaluation.Therefore, in this paper, we introduce a novel game named BrainKing based on the “Who is undercover” and “Twenty Questions” for evaluating LLM capabilities under incomplete information scenarios. It requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers. By setting up easy, medium, and hard difficulty modes, we comprehensively assess the performance of LLMs across various aspects. Our results reveal the capabilities and limitations of LLMs in BrainKing, providing significant insights of LLM problem-solving levels.

Yuyan Chen, Songzhou Yan, Qingpei Guo, Jiyuan Jia, Zhixu Li, Yanghua Xiao

In the era of social media video platforms, popular “hot-comments” play a crucial role in attracting user impressions of short-form videos, making them vital for marketing and branding purpose. However, existing research predominantly focuses on generating descriptive comments or “danmaku” in English, offering immediate reactions to specific video moments. Addressing this gap, our study introduces HOTVCOM, the largest Chinese video hot-comment dataset, comprising 94k diverse videos and 137 million comments. We also present the ComHeat framework, which synergistically integrates visual, auditory, and textual data to generate influential hot-comments on the Chinese video dataset. Empirical evaluations highlight the effectiveness of our framework, demonstrating its excellence on both the newly constructed and existing datasets.

Rui Pan, Shuo Xing, Shizhe Diao, Wenhe Sun, Xiang Liu, KaShun Shum, Jipeng Zhang, Renjie Pi, Tong Zhang

Since the emergence of large language models, prompt learning has become a popular method for optimizing and customizing these models. Special prompts, such as Chain-of-Thought, have even revealed previously unknown reasoning capabilities within these models. However, the progress of discovering effective prompts has been slow, driving a desire for general prompt optimization methods. Unfortunately, few existing prompt learning methods satisfy the criteria of being truly “general”, i.e., automatic, discrete, black-box, gradient-free, and interpretable all at once. In this paper, we introduce metaheuristics, a branch of discrete non-convex optimization methods with over 100 options, as a promising approach to prompt learning. Within our paradigm, we test six typical methods: hill climbing, simulated annealing, genetic algorithms with/without crossover, tabu search, and harmony search, demonstrating their effectiveness in white-box and black-box prompt learning. Furthermore, we show that these methods can be used to discover more human-understandable prompts that were previously unknown in both reasoning and image generation tasks, opening the door to a cornucopia of possibilities in prompt optimization.

Yuyan Chen, Songzhou Yan, Sijia Liu, Yueze Li, Yanghua Xiao

Emotional intelligence in large language models (LLMs) is of great importance in Natural Language Processing. However, the previous research mainly focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs’ overall emotional intelligence. Therefore, this paper presents a novel framework named EmotionQueen for evaluating the emotional intelligence of LLMs. The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition. LLMs are requested to recognize important event or implicit emotions and generate empathetic response.We also design two metrics to evaluate LLMs’ capabilities in recognition and response for emotion-related statements. Experiments yield significant conclusions about LLMs’ capabilities and limitations in emotion intelligence.

Xinnan Guo, Qian Zhu, Qiuhui Shi, Xuan Lin, Liubin Wang, DaqianLi DaqianLi, Yongrui Chen

Incomplete utterance rewriting (IUR) aims to reconstruct the utterance with omitted information and pronouns to be standalone and complete based on the context. The existing works predominantly focus on simple ellipsis and coreference problems in brief multi-turn dialogues. But in actual scenarios: 1) the context of the dialogues frequently comprises multiple similar candidates for ellipsis and coreference resolution, pouring to confuse. 2) the number of turns tends to be more extensive, while the content with various topics also grows more complex. This paper proposes a novel method called CaT to address these issues. In particular, we first devise a tacker model, distilled from GPT4-turbo, to adopt Context Tracking that dynamically updates a list of key phrases turn by turn, as accurate candidates for ellipsis and coreference resolution. Second, we further present the Dynamic Context Introduction mechanism to filter irrelevant preceding contexts that are not relied on by any element within the key phrase list to condense extended dialogues. Comprehensive experiments indicate that our solution provides a significant improvement over the existing baselines, and achieves state-of-the-art on three benchmarks.

Yongqiang Ma, Lizhi Qing, Jiawei Liu, Yangyang Kang, Yue Zhang, Wei Lu, Xiaozhong Liu, Qikai Cheng

Evaluating large language models (LLMs) is fundamental, particularly in the context of practical applications. Conventional evaluation methods, typically designed primarily for LLM development, yield numerical scores that ignore the user experience. Therefore, our study shifts the focus from model-centered to human-centered evaluation in the context of AI-powered writing assistance applications. Our proposed metric, termed “Revision Distance,” utilizes LLMs to suggest revision edits that mimic the human writing process. It is determined by counting the revision edits generated by LLMs. Benefiting from the generated revision edit details, our metric can provide a self-explained text evaluation result in a human-understandable manner beyond the context-independent score. Our results show that for the easy-writing task, “Revision Distance” is consistent with established metrics (ROUGE, Bert-score, and GPT-score), but offers more insightful, detailed feedback and better distinguishes between texts. Moreover, in the context of challenging academic writing tasks, our metric still delivers reliable evaluations where other metrics tend to struggle. Furthermore, our metric also holds significant potential for scenarios lacking reference texts.

Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang

Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge and style of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing agents at both individual and group levels of social interactions. SocialBench is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. We conduct comprehensive evaluations on this benchmark using mainstream LLMs. We find that agents excelling in individual level does not imply their proficiency in group level. Experimental results on SocialBench confirm its significance as a testbed for assessing the social interaction of role-playing agents. The benchmark is publicly accessible at https://github.com/X-PLUG/RoleInteract.

Hanbin Wang, Zhenghao Liu, Shuo Wang, Ganqu Cui, Ning Ding, Zhiyuan Liu, Ge Yu

This paper introduces INTERVENOR (INTERactiVE chaiN Of Repair), a system designed to emulate the interactive code repair processes observed in humans, encompassing both code diagnosis and code repair. INTERVENOR prompts Large Language Models (LLMs) to play distinct roles during the code repair process, functioning as both a Code Learner and a Code Teacher. Specifically, the Code Learner is tasked with adhering to instructions to generate or repair code, while the Code Teacher is responsible for crafting a Chain-of-Repair (CoR) to serve as guidance for the Code Learner. During generating the CoR, the Code Teacher needs to check the generated codes from Code Learner and reassess how to address code bugs based on error feedback received from compilers. Experimental results demonstrate that INTERVENOR surpasses baseline models, exhibiting improvements of approximately 18% and 4.3% over GPT-3.5 in code generation and code translation tasks, respectively. Our further analyses show that CoR is effective to illuminate the reasons behind bugs and outline solution plans in natural language. With the feedback of code compilers, INTERVENOR can accurately identify syntax errors and assertion errors and provide precise instructions to repair codes. All data and codes are available at [https://github.com/NEUIR/INTERVENOR](https://github.com/NEUIR/INTERVENOR).

Yudong Wang, Chang Ma, Qingxiu Dong, Zhifang Sui, Lingpeng Kong, Jingjing Xu

With promising yet saturated results in high-resource settings, low-resource datasets have gradually become crucial benchmarks (e.g., BigBench Hard, superGLUE) for evaluating the learning ability of advanced neural networks. In this work, we find that there exists a set of “hard examples” in low-resource settings that challenge neural networks but are not well evaluated, which causes over-estimated performance. We first give a theoretical analysis on which factors bring the difficulty of low-resource learning. It then motivates us to propose a challenging benchmark Achilles-Bench to better evaluate the learning ability, which covers 11 datasets, including 8 natural language process (NLP) datasets and 3 computer vision (CV) datasets. Experiments on a wide range of models show that neural networks, even pre-trained language models, have sharp performance drops on our benchmark, demonstrating the effectiveness of evaluating the weaknesses of neural networks. On NLP tasks, we surprisingly find that despite better results on traditional low-resource benchmarks, pre-trained networks, does not show performance improvements on our benchmarks. there is still a large robustness gap between existing models and human-level performance, highlighting the need for robust low-resource learning models.

Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin 等

Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing. However, three core challenges remain: inefficient knowledge retrieval, mistakes of retrieval adversely impacting semantic parsing, and the complexity of previous KBQA methods. To tackle these challenges, we introduce ChatKBQA, a novel and simple generate-then-retrieve KBQA framework, which proposes first generating the logical form with fine-tuned LLMs, then retrieving and replacing entities and relations with an unsupervised retrieval method, to improve both generation and retrieval more directly. Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ. This work can also be regarded as a new paradigm for combining LLMs with knowledge graphs (KGs) for interpretable and knowledge-required question answering.

Shuo Zhang, Liangming Pan, Junzhou Zhao, William Yang Wang

Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers. Yet even with the correct groundings in the reference, they can ignore them and rely on wrong groundings or their inherent biases to hallucinate when users, being largely unaware of the specifics of the stored information, pose questions that might not directly correlate with the retrieved groundings. In this work, we formulate this knowledge alignment problem and introduce MixAlign, a framework that interacts with both the human user and the knowledge base to obtain and integrate clarifications on how the user question relates to the stored information. MixAlign employs a language model to achieve automatic knowledge alignment and, if necessary, further enhances this alignment through human user clarifications. Experimental results highlight the crucial role of knowledge alignment in boosting model performance and mitigating hallucination, with improvements noted up to 22.2% and 27.1% respectively. We also demonstrate the effectiveness of MixAlign in improving knowledge alignment by producing high-quality, user-centered clarifications.

Wenxin Mao, Ruiqi Wang, Jiyu Guo, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu

Large Language Model (LLM)-based approach has become the mainstream for Text-to-SQL task and achieves remarkable performance. In this paper, we augment the existing prompt engineering methods by exploiting the database content and execution feedback. Specifically, we introduce DART-SQL, which comprises two key components: (1) Question Rewriting: DART-SQL rewrites natural language questions by leveraging database content information to eliminate ambiguity. (2) Execution-Guided Refinement: DART-SQL incorporates database content information and utilizes the execution results of the generated SQL to iteratively refine the SQL. We apply this framework to the two LLM-based approaches (DAIL-SQL and C3) and test it on four widely used benchmarks (Spider-dev, Spider-test, Realistic and DK). Experiments show that our framework for DAIL-SQL and C3 achieves an average improvement of 12.41% and 5.38%, respectively, in terms of execution accuracy(EX) metric.

Sheng Wang, Liheng Chen, Jiyue Jiang, Boyang Xue, Lingpeng Kong, Chuan Wu

With the remarkable capabilities, large language models (LLMs) have emergedas essential elements in numerous NLP applications, while parameter-efficientfinetuning, especially LoRA, has gained popularity as a lightweight approachfor model customization. Meanwhile, various dropout methods, initially designedfor full finetuning with all the parameters updated, alleviates overfittingassociated with excessive parameter redundancy. Hence, a possible contradictionarises from negligible trainable parameters of LoRA and the effectiveness ofprevious dropout methods, which has been largely overlooked. To fill this gap,we first confirm that parameter-efficient LoRA is also overfitting-prone. Wethen revisit transformer-specific dropout methods, and establish theirequivalence and distinctions mathematically and empirically. Building upon thiscomparative analysis, we introduce a unified framework for a comprehensiveinvestigation, which instantiates these methods based on dropping position,structural pattern and compensation measure. Through this framework, we revealthe new preferences and performance comparisons of them when involved withlimited trainable parameters. This framework also allows us to amalgamate themost favorable aspects into a novel dropout method named HiddenKey. Extensiveexperiments verify the remarkable superiority and sufficiency of HiddenKeyacross multiple models and tasks, which highlights it as the preferred approachfor high-performance and parameter-efficient finetuning of LLMs.

Jiang Li, Xiangdong Su, Fujun Zhang, Guanglai Gao

Knowledge graph embedding (KGE) is extensively employed for link prediction by representing entities and relations as low-dimensional vectors. In real-world scenarios, knowledge graphs (KGs) usually encompass diverse domains, which poses challenges to KG representations. However, existing KGE methods rarely make domain constraints on the embedding distribution of multi-domain KGs, leading to the embedding overlapping of different domains and performance degradation of link prediction. To address this challenge, we propose Dual Archimedean Spiral Knowledge Graph Embedding (DuASE), a low-dimensional KGE model for multi-domain KGs. DuASE is inspired by our discovery that relation types can distinguish entities from different domains. Specifically, DuASE encodes entities with the same relation on the same Archimedean spiral, allowing it to differentiate the entities from different domains. To avoid embedding overlapping across domains, DuASE further makes the head and the tail spirals in the same triplet cluster to their respective domain space by a regularization function. Thus, DuASE can better capture the domain information and the dependencies between entities when modeling the multi-domain KGs, leading to improved KG representations. We validate the effectiveness of DuASE on the novel multi-domain dataset (n-MDKG) introduced in this study and three other benchmark datasets.

Di Wu, Da Yin, Kai-Wei Chang

Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references. This scheme fails to recognize systems that generate keyphrases semantically equivalent to the references or diverse keyphrases that carry practical utility. To better assess the capability of keyphrase systems, we propose KPEval, a comprehensive evaluation framework consisting of four critical aspects: reference agreement, faithfulness, diversity, and utility. For each aspect, we design semantic-based metrics to reflect the evaluation objectives. Meta-evaluation studies demonstrate that our evaluation strategy correlates better with human preferences compared to a range of previously proposed metrics. Using KPEval, we re-evaluate 23 keyphrase systems and discover that (1) established model comparison results have blind-spots especially when considering reference-free evaluation; (2) large language models are underestimated by prior evaluation works; and (3) there is no single best model that can excel in all the aspects.

Junfeng Fang, Shuai Zhang, Chang Wu, Zhengyi Yang, Zhiyuan Liu, Sihang Li, Kun Wang, Wenjie Du, Xiang Wang

Molecular Relational Learning (MRL), aiming to understand interactions between molecular pairs, plays a pivotal role in advancing biochemical research. Recently, the adoption of large language models (LLMs), known for their vast knowledge repositories and advanced logical inference capabilities, has emerged as a promising way for efficient and effective MRL. Despite their potential, these methods predominantly rely on textual data, thus not fully harnessing the wealth of structural information inherent in molecular graphs. Moreover, the absence of a unified framework exacerbates the issue of insufficient data exploitation, as it hinders the sharing of interaction mechanism learned across various datasets. To address these challenges, this work proposes a novel LLM-based multi-modal framework for molecular interaction modeling following Chain-of-Thought (CoT) theory, termed MolTC, which effectively integrate graphical information of two molecules in pair. To train this integrated framework efficiently, we introduce a *multi-hierarchical CoT theory* to refine its training paradigm, and conduct a comprehensive *Molecular Interactive Instructions* dataset for the development of biochemical LLMs involving MRL.Our experiments,conducted across various datasets involving over 4,000,000 molecular pairs, exhibit the superiority of our method over current GNN and LLM-based baselines. Code is available at https://github.com/MangoKiller/MolTC.