ACL 2024 论文列表

In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs). LLMs often struggle with this task, leading to the generation of inaccurate or misleading responses. This issue mainly arises from their limited ability to handle evolving factual knowledge and complex temporal logic. To overcome these limitations, we propose Abstract Reasoning Induction (ARI) framework, which divides temporal reasoning into two distinct phases: Knowledge agnostic and Knowledge-based. This framework offers factual knowledge support to LLMs while minimizing the incorporation of extraneous noisy data. Concurrently, informed by the principles of constructivism, ARI provides LLMs the capability to engage in proactive, self-directed learning from both correct and incorrect historical reasoning samples. By teaching LLMs to actively construct knowledge and methods, it can significantly boosting their temporal reasoning abilities. Our approach achieves significant improvements, with relative gains of 29.7% and 9.27% on two temporal QA datasets, underscoring its efficacy in advancing temporal reasoning in LLMs. The code can be found at https: //github.com/czy1999/ARI-QA.

A wide body of evidence shows that human language processing difficulty is predicted by the information-theoretic measure surprisal, a word’s negative log probability in context. However, it is still unclear how to best estimate these probabilities needed for predicting human processing difficulty – while a long-standing belief held that models with lower perplexity would provide more accurate estimates of word predictability, and therefore lead to better reading time predictions, recent work has shown that for very large models, psycholinguistic predictive power decreases. One reason could be that language models might be more confident of their predictions than humans, because they have had exposure to several magnitudes more data. In this paper, we test what effect temperature-scaling of large language model (LLM) predictions has on surprisal estimates and their predictive power of reading times of English texts. Firstly, we show that calibration of large language models typically improves with model size, i.e. poorer calibration cannot account for poorer fit to reading times. Secondly, we find that temperature-scaling probabilities lead to a systematically better fit to reading times (up to 89% improvement in delta log likelihood), across several reading time corpora. Finally, we show that this improvement in fit is chiefly driven by words that are composed of multiple subword tokens.

Recently, there is a surge in interest surrounding video large language models (Video LLMs). However, existing benchmarks fail to provide a comprehensive feedback on the temporal perception ability of Video LLMs. On the one hand, most of them are unable to distinguish between different temporal aspects (e.g., speed, direction) and thus cannot reflect the nuanced performance on these specific aspects. On the other hand, they are limited in the diversity of task formats (e.g., only multi-choice QA), which hinders the understanding of how temporal perception performance may vary across different types of tasks. Motivated by these two problems, we propose the TempCompass benchmark, which introduces a diversity of temporal aspects and task formats. To collect high-quality test data, we devise two novel strategies: (1) In video collection, we construct conflicting videos that share the same static content but differ in a specific temporal aspect, which prevents Video LLMs from leveraging single-frame bias or language priors. (2) To collect the task instructions, we propose a paradigm where humans first annotate meta-information for a video and then an LLM generates the instruction. We also design an LLM-based approach to automatically and accurately evaluate the responses from Video LLMs. Based on TempCompass, we comprehensively evaluate 9 state-of-the-art (SOTA) Video LLMs and 3 Image LLMs, and reveal the discerning fact that these models exhibit notably poor temporal perception ability.

Mobile app user interfaces (UIs) are rich with action, text, structure, and image content that can be utilized to learn generic UI representations for tasks like automating user commands, summarizing content, and evaluating the accessibility of user interfaces. Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities.To combat this, we propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current UI and local action taken. Our approach requires joint reasoning over elements and entire screens, resulting in improved UI features: on generation tasks, UI agents trained with Textual Foresight outperform state-of-the-art by 2% with 28x fewer images. We train with our newly constructed mobile app dataset, OpenApp, which results in the first public dataset for app UI representation learning. OpenApp enables new baselines, and we find Textual Foresight improves average task performance over them by 5.7% while having access to 2x less data.

Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents struggle with seeking clarification and grasping precise user intentions. To bridge this gap, we introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users’ implicit intentions through explicit queries. Next, we propose the incorporation of model experts as the upstream in agent designs to enhance user-agent interaction. Employing IN3, we empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires about user intentions, and refines them into actionable goals before starting downstream agent task execution. Integrating it into the XAgent framework, we comprehensively evaluate the enhanced agent system regarding user instruction understanding and execution, revealing that our approach notably excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency.

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models.Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the teacher LLM, such as GPT-4, for gathering an ample number of demonstrations; 2) the teacher LLM might provide imperfect outputs with a negative impact on the student’s learning process. To enhance sample efficiency within resource-constrained, imperfect teacher scenarios, we propose a three-component framework leveraging three signal types. The first signal is the student’s self-consistency (consistency of student multiple outputs), which is a proxy of the student’s confidence. Specifically, we introduce a ”teaching assistant” (TA) model to assess the uncertainty of both the student’s and the teacher’s outputs via confidence scoring, which serves as another two signals for student training. Furthermore, we propose a two-stage training schema to first warm up the student with a small proportion of data to better utilize student’s signal. Experiments have shown the superiority of our proposed framework for four complex reasoning tasks. On average, our proposed two-stage framework brings a relative improvement of up to 20.79% compared to fine-tuning without any signals across datasets.

Large Language Models (LLMs) can teach small language models (SLMs) to solve complex reasoning tasks (e.g., mathematical question answering) by Chain-of-thought Distillation (CoTD). Specifically, CoTD fine-tunes SLMs by utilizing rationales generated from LLMs such as ChatGPT. However, CoTD has certain limitations that make it unsuitable for knowledge-intensive multi-hop question answering: 1) SLMs have a very limited capacity in memorizing required knowledge compared to LLMs. 2) SLMs do not possess the same powerful integrated abilities in question understanding and knowledge reasoning as LLMs. To address the above limitations, we introduce Decompose-and-Response Distillation (D&R Distillation), which distills two student models, namely Decomposer and Responser separately. The two models solve a knowledge-intensive multi-hop question through an interactive process of asking and answering subquestions. Our method offers two advantages: 1) SLMs have the capability to access external knowledge to address subquestions, which provides more comprehensive knowledge for multi-hop questions. 2) By employing simpler subquestions instead of complex CoT reasoning, SLMs effectively mitigate task complexity and decrease data prerequisites. Experimental results on three knowledge-intensive multi-hop question answering datasets demonstrate that D&R Distillation can surpass previous CoTD methods, even with much less training data.

Existing large language models struggle to support numerous low-resource languages, particularly the extremely low-resource ones, for which there is minimal training data available for effective parameter updating. We thus investigate whether LLMs can learn a new language on the fly solely through prompting. To study this question, we collect a research suite for Zhuang, a language supported by no LLMs currently. We introduce DiPMT++, a framework for adapting LLMs to unseen languages by in-context learning. Using a dictionary and 5K parallel sentences only, DiPMT++ significantly enhances the performance of GPT-4 from 0 to 16 BLEU for Chinese-to-Zhuang translation and achieves 32 BLEU for Zhuang-to-Chinese translation. We also validate the effectiveness of our framework on Kalamang, another unseen language. Furthermore, we demonstrate the practical utility of DiPMT++ in aiding humans in translating completely unseen languages, which could contribute to the preservation of linguistic diversity.

Aligning Large Language Models (LLMs) with human intentions and values is crucial yet challenging. Current methods primarily rely on human preferences, which are costly and insufficient in capturing nuanced feedback expressed in natural language. In this paper, we present Self-Refinement Tuning (SRT), a method that leverages model feedback for alignment, thereby reducing reliance on human annotations. SRT uses a base language model (e.g., Tulu2) to generate initial responses, which are critiqued and refined by a more advanced model (e.g., GPT-4-Turbo). This process enables the base model to self-evaluate and improve its outputs, facilitating continuous learning. SRT further optimizes the model by learning from its self-generated feedback and refinements, creating a feedback loop that promotes model improvement. Our empirical evaluations demonstrate that SRT significantly outperforms strong baselines across diverse tasks and model sizes. When applied to a 70B parameter model, SRT increases the win rate from 9.6% to 25.8% on the AlpacaEval 2.0 benchmark, surpassing well-established systems such as GPT-4-0314, Claude 2, and Gemini. Our analysis highlights the crucial role of language feedback in the success of SRT, suggesting potential for further exploration in this direction.

Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks. One example is permutation sensitivity, where LLMs’ outputs may significantly vary depending on the order of the input options. While debiasing techniques can mitigate these issues, and yield better performance and reliability, they often come with a high computational cost at inference. This paper addresses this inefficiency at inference time. The aim is to distill the capabilities of a computationally intensive, debiased, teacher model into a more compact student model. We explore two variants of student models: one based on pure distillation, and the other on an error-correction approach for more complex tasks, where the student corrects a single biased decision from the teacher to achieve a debiased output. Our approach is general and can be applied to both black-box and white-box LLMs. Furthermore, we demonstrate that our compact, encoder-only student models can outperform their larger, biased teacher counterparts, achieving better results with significantly fewer parameters.

In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the outcome of our experiments, we present TaxoLLaMA, the “all-in-one” model for taxonomy-related tasks, lightweight due to 4-bit quantization and LoRA. TaxoLLaMA achieves 11 SOTA results, and 4 top-2 results out of 16 tasks on the Taxonomy Enrichment, Hypernym Discovery, Taxonomy Construction, and Lexical Entailment tasks. Moreover, it demonstrates a very strong zero-shot performance on Lexical Entailment and Taxonomy Construction with no fine-tuning. We also explore its hidden multilingual and domain adaptation capabilities with a little tuning or few-shot learning. All datasets, code, and pre-trained models are available online (code: https://github.com/VityaVitalich/TaxoLLaMA)

Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. Techniques like instruction tuning have effectively enhanced the proficiency of LLMs in the downstream task of machine translation. However, the existing approaches fail to yield satisfactory translation outputs that match the quality of supervised neural machine translation (NMT) systems. One plausible explanation for this discrepancy is that the straightforward prompts employed in these methodologies are unable to fully exploit the acquired instruction-following capabilities. To this end, we propose the TasTe framework, which stands for translating through self-reflection. The self-reflection process includes two stages of inference. In the first stage, LLMs are instructed to generate preliminary translations and conduct self-assessments on these translations simultaneously. In the second stage, LLMs are tasked to refine these preliminary translations according to the evaluation results. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods. Our work presents a promising approach to unleash the potential of LLMs and enhance their capabilities in MT. The codes and datasets are open-sourced at https://github.com/YutongWang1216/ReflectionLLMMT.

Large Language Model (LLM)-enhanced agents become increasingly prevalent in Human-AI communication, offering vast potential from entertainment to professional domains. However, current multi-modal dialogue systems overlook the acoustic information present in speech, which is crucial for understanding human communication nuances. This oversight can lead to misinterpretations of speakers’ intentions, resulting in inconsistent or even contradictory responses within dialogues. To bridge this gap, in this paper, we propose PerceptiveAgent, an empathetic multi-modal dialogue system designed to discern deeper or more subtle meanings beyond the literal interpretations of words through the integration of speech modality perception. Employing LLMs as a cognitive core, PerceptiveAgent perceives acoustic information from input speech and generates empathetic responses based on speaking styles described in natural language. Experimental results indicate that PerceptiveAgent excels in contextual understanding by accurately discerning the speakers’ true intentions in scenarios where the linguistic meaning is either contrary to or inconsistent with the speaker’s true feelings, producing more nuanced and expressive spoken dialogues. Code is publicly available at: https://github.com/Haoqiu-Yan/PerceptiveAgent.

How-to procedures, such as how to plant a garden, are now used by millions of users, but sometimes need customizing to meet a user’s specific needs, e.g., planting a garden without pesticides. Our goal is to measure and improve an LLM’s ability to perform such customization. Our approach is to test several simple multi-LLM-agent architectures for customization, as well as an end-to-end LLM, using a new evaluation set, called CustomPlans, of over 200 WikiHow procedures each with a customization need. We find that a simple architecture with two LLM agents used sequentially performs best, one that edits a generic how-to procedure and one that verifies its executability, significantly outperforming (10.5% absolute) an end-to-end prompted LLM. This suggests that LLMs can be configured reasonably effectively for procedure customization. This also suggests that multi-agent editing architectures may be worth exploring further for other customization applications (e.g. coding, creative writing) in the future.

Tables contrast with unstructured text data by its structure to organize the information.In this paper, we investigate the efficiency of various LLMs in interpreting tabular data through different prompting strategies and data formats. Our analysis extends across six benchmarks for table-related tasks such as question-answering and fact-checking. We pioneer in the assessment of LLMs’ performance on image-based table representation. Specifically, we compare five text-based and three image-based table representations, revealing the influence of representation and prompting on LLM performance. We hope our study provides researchers insights into optimizing LLMs’ application in table-related tasks.

A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL, with a 7.6% absolute increase in Avg. JGA and an 11% absolute rise in BWT metrics over existing state-of-the-art methods. The source code is provided for reproducibility.

Long-form Table Question Answering (LFTQA) requires systems to generate paragraph long and complex answers to questions over tabular data. While Large language models based systems have made significant progress, it often hallucinates, especially when the task involves complex reasoning over tables. To tackle this issue, we propose a new LLM-based framework, TaPERA, for LFTQA tasks. Our framework uses a modular approach that decomposes the whole process into three sub-modules: 1) QA-based Content Planner that iteratively decomposes the input question into sub-questions; 2) Execution-based Table Reasoner that produces executable Python program for each sub-question; and 3) Answer Generator that generates long-form answer grounded on the program output. Human evaluation results on the FeTaQA and QTSumm datasets indicate that our framework significantly improves strong baselines on both accuracy and truthfulness, as our modular framework is better at table reasoning, and the long-form answer is always consistent with the program output. Our modular design further provides transparency as users are able to interact with our framework by manually changing the content plans.

The recent advances in natural language processing have predominantly favored well-resourced English-centric models, resulting in a significant gap with low-resource languages. In this work, we introduce TURNA, a language model developed for the low-resource language Turkish and is capable of both natural language understanding and generation tasks.TURNA is pretrained with an encoder-decoder architecture based on the unified framework UL2 with a diverse corpus that we specifically curated for this purpose. We evaluated TURNA with three generation tasks and five understanding tasks for Turkish. The results show that TURNA outperforms several multilingual models in both understanding and generation tasks and competes with monolingual Turkish models in understanding tasks.

Document-level relation extraction aims to categorize the association between any two entities within a document.We find that previous methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels. For example, in the ReDocRED benchmark dataset, state-of-the-art methods trained on the large-scale, lower-quality, distantly supervised training data generally do not perform better than those trained solely on the smaller, high-quality, human-annotated training data. To unlock the full potential of large-scale noisy training data for document-level relation extraction, we propose TTM-RE, a novel approach that integrates a trainable memory module, known as the Token Turing Machine, with a noisy-robust loss function that accounts for the positive-unlabeled setting. The trainable memory module enhances knowledge extraction from the large-scale noisy training dataset through an explicit learning of the memory tokens and a soft integration of the learned memory tokens into the input representation, thereby improving the model’s effectiveness for the final relation classification. Extensive experiments on ReDocRED, a benchmark dataset for document-level relation extraction, reveal that TTM-RE achieves state-of-the-art performance (with an absolute F1 score improvement of over 3%). Ablation studies further illustrate the superiority of TTM-RE in other domains (the ChemDisGene dataset in the biomedical domain) and under highly unlabeled settings.