Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual rules in the environment. Existing methods require either costly gradient computation or lengthy in-context demonstrations. In this paper, we propose AutoPlan, an approach to guide LLM-based agents to accomplish interactive decision-making tasks. AutoPlan augments the LLM prompt with a task-solving plan and optimizes it through iterative experience collection and reflection. Our experiments show that AutoPlan, though using no in-context demonstrations, achieves success rates on par with the baselines using human-written demonstrations on ALFWorld and even outperforms them by 8% on HotpotQA. The code is available at https://github.com/owaski/AutoPlan.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
Fine-tuning all the layers of a pre-trained neural language encoder (either using all the parameters or using parameter-efficient methods) is often the de-facto way of adapting it to a new task. We show evidence that for different downstream language tasks, fine-tuning only a subset of layers is sufficient to obtain performance that is close to and often better than fine-tuning all the layers in the language encoder. We propose an efficient metric based on the diagonal of the Fisher information matrix (FIM score), to select the candidate layers for selective fine-tuning. We show, empirically on GLUE and SuperGLUE tasks and across distinct language encoders, that this metric can effectively select layers leading to a strong downstream performance. Our work highlights that task-specific information corresponding to a given downstream task is often localized within a few layers, and tuning only those is sufficient for strong performance. Additionally, we demonstrate the robustness of the FIM score to rank layers in a manner that remains constant during the optimization process.
Multi-path voting methods like Self-consistency have been used to mitigate reasoning errors in large language models caused by factual errors and illusion generation. However, these methods require excessive computing resources as they generate numerous reasoning paths for each problem. And our experiments show that on the arithmetic reasoning task, SVAMP, half of the problems fail to obtain noticeable accuracy gains when voting with more than three paths. In this paper, we propose a novel multi-path voting technique called Dynamic Voting, which effectively reduces the number of reasoning paths during multi-path voting while preserving accuracies by applying early exiting for problems that large language models can confidently solve. Experimental evaluations on arithmetic, commonsense, and symbolic reasoning tasks under few-shot and zero-shot settings demonstrate that Dynamic Voting achieves comparable accuracies employing significantly fewer reasoning paths. Notably, one of our Dynamic Voting strategies outperforms Self-consistency using only 24.7% of the number of paths on the LetterConcat task in the few-shot setting. Furthermore, Dynamic Voting showcases strong robustness in threshold selection. It also demonstrates excellent generalizability when combined with other voting techniques, different models, and diverse prompts.
Simultaneous machine translation (SiMT) generates translation while reading the whole source sentence. However, existing SiMT models are typically trained using the same reference disregarding the varying amounts of available source information at different latency. Training the model with ground-truth at low latency may introduce forced anticipations, whereas utilizing reference consistent with the source word order at high latency results in performance degradation. Consequently, it is crucial to train the SiMT model with appropriate reference that avoids forced anticipations during training while maintaining high quality. In this paper, we propose a novel method that provides tailored reference for the SiMT models trained at different latency by rephrasing the ground-truth. Specifically, we introduce the tailor, induced by reinforcement learning, to modify ground-truth to the tailored reference. The SiMT model is trained with the tailored reference and jointly optimized with the tailor to enhance performance. Importantly, our method is applicable to a wide range of current SiMT approaches. Experiments on three translation tasks demonstrate that our method achieves state-of-the-art performance in both fixed and adaptive policies.
Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning
PDF ↗Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students’ mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions’ rationales when attempting to correct students’ answers. Three research questions are formulated.
Lately, propelled by phenomenal advances around the transformer architecture, the legal NLP field has enjoyed spectacular growth. To measure progress, well-curated and challenging benchmarks are crucial. Previous efforts have produced numerous benchmarks for general NLP models, typically based on news or Wikipedia. However, these may not fit specific domains such as law, with its unique lexicons and intricate sentence structures. Even though there is a rising need to build NLP systems for languages other than English, many benchmarks are available only in English and no multilingual benchmark exists in the legal NLP field. We survey the legal NLP literature and select 11 datasets covering 24 languages, creating LEXTREME. To fairly compare models, we propose two aggregate scores, i.e., dataset aggregate score and language aggregate score. Our results show that even the best baseline only achieves modest results, and also ChatGPT struggles with many tasks. This indicates that LEXTREME remains a challenging task with ample room for improvement. To facilitate easy use for researchers and practitioners, we release LEXTREME on huggingface along with a public leaderboard and the necessary code to evaluate models. We also provide a public Weights and Biases project containing all runs for transparency.
Keyphrase generation (KG) aims to generate a set of summarizing words or phrases given a source document, while keyphrase extraction (KE) aims to identify them from the text. Because the search space is much smaller in KE, it is often combined with KG to predict keyphrases that may or may not exist in the corresponding document. However, current unified approaches adopt sequence labeling and maximization-based generation that primarily operate at a token level, falling short in observing and scoring keyphrases as a whole. In this work, we propose SimCKP, a simple contrastive learning framework that consists of two stages: 1) An extractor-generator that extracts keyphrases by learning context-aware phrase-level representations in a contrastive manner while also generating keyphrases that do not appear in the document; 2) A reranker that adapts scores for each generated phrase by likewise aligning their representations with the corresponding document. Experimental results on multiple benchmark datasets demonstrate the effectiveness of our proposed approach, which outperforms the state-of-the-art models by a significant margin.
Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Methods
PDF ↗The majority of existing work on sign language recognition encodes signed videos without explicitly acknowledging the phonological attributes of signs. Given that handshape is a vital parameter in sign languages, we explore the potential of handshape-aware sign language recognition. We augment the PHOENIX14T dataset with gloss-level handshape labels, resulting in the new PHOENIX14T-HS dataset. Two unique methods are proposed for handshape-inclusive sign language recognition: a single-encoder network and a dual-encoder network, complemented by a training strategy that simultaneously optimizes both the CTC loss and frame-level cross-entropy loss. The proposed methodology consistently outperforms the baseline performance. The dataset and code can be accessed at: www.anonymous.com.
On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study
PDF ↗Modern deep models for summarization attains impressive benchmark performance, but they are prone to generating miscalibrated predictive uncertainty. This means that they assign high confidence to low-quality predictions, leading to compromised reliability and trustworthiness in real-world applications. Probabilistic deep learning methods are common solutions to the miscalibration problem. However, their relative effectiveness in complex autoregressive summarization tasks are not well-understood. In this work, we thoroughly investigate different state-of-the-art probabilistic methods’ effectiveness in improving the uncertainty quality of the neural summarization models, across three large-scale benchmarks with varying difficulty using our newly introduced evaluation protocol. We show that the probabilistic methods consistently improve the model’s generation and uncertainty quality, leading to improved selective generation performance (i.e., abstaining from low-quality summaries) in practice. We also reveal notable failure patterns of probabilistic methods widely-adopted in NLP community (e.g., Deep Ensemble and Monte Carlo Dropout), cautioning the importance of choosing appropriate method for the data setting.
Thanks in part to the availability of copious annotated resources for some entity categories, existing studies have achieved superior performance in multimodal named entity recognition (MNER). However, in the real-world scenario, it is infeasible to enumerate all entity categories in advance. Therefore, in this paper, we formulate a new few-shot multimodal named entity recognition (FewMNER) task, which aims to effectively locate and identify named entities for a text-image pair only using a small number of labeled examples. Further, we explore the merit of in-context learning (ICL) and propose a novel framework to deal with FewMNER, where three points are taken into account: i.e., converting visual modality, selecting useful examples, and designing an effective task demonstration. Specifically, we first employ an image caption model to convert images into textual descriptions, enabling large language models to absorb information from visual modality. Then, we use the ranking of the sum of similarity rankings from both text and image modalities to select k-nearest examples, which form a demonstration context. Finally, we utilize the MNER definition and the meaning of each entity category as effective instruction. Extensive experimental results demonstrate that our framework outperforms baselines under several few-shot settings.
Topic segmentation, in the context of natural language processing, is the process of finding boundaries in a sequence of sentences that separate groups of adjacent sentences at shifts in semantic meaning. Currently, assessing the quality of a segmentation is done by comparing segmentation boundaries selected by a human or algorithm to those selected by a known good reference. This means that it is not possible to quantify the quality of a segmentation without a human annotator, which can be costly and time consuming. This work seeks to improve assessment of segmentation by proposing a reference-free segmentation quality index (SegReFree). The metric takes advantage of the fact that segmentation at a sentence level generally seeks to identify segment boundaries at semantic boundaries within the text. The proposed metric uses a modified cluster validity metric with semantic embeddings of the sentences to determine the quality of the segmentation. Multiple segmentation data sets are used to compare our proposed metric with existing reference-based segmentation metrics by progressively degrading the reference segmentation while computing all possible metrics; through this process, a strong correlation with existing segmentation metrics is shown. A Python library implementing the metric is released under the GNU General Public License and the repository is available at https://github.com/evan-person/reference_free_segmentation_metric.
High-quality argumentative information in low resources approaches improve counter-narrative generation
PDF ↗It has been shown that high quality fine-tuning boosts the performance of language models, even if the size of the fine-tuning is small. In this work we show how highly targeted fine-tuning improves the task of hate speech counter-narrative generation in user-generated text, even for very small sizes of training (1722 counter-narratives for English and 355 for Spanish). Providing a small subset of examples focusing on single argumentative strategies, together with the argumentative analysis relevant to that strategy, yields counter-narratives that are as satisfactory as providing the whole set of counter-narratives. We also show that a good base model is required for the fine-tuning to have a positive impact. Indeed, for Spanish, the counter-narratives obtained without fine-tuning are mostly unacceptable, and, while fine-tuning improves their overall quality, the performance still remains quite unsatisfactory.
Reducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models
PDF ↗Recently, aspect-based sentiment analysis (ABSA) models have yielded promising results. However, they are susceptible to learning spurious correlations between certain words of the input text and output labels while modeling the sentiment feature of the aspect. This spurious correlation will potentially undermine the performance of ABSA models. One direct solution for this problem is to make the model see and learn an explanation of sentiment expression rather than certain words. Motivated by this, we exploit explanations for the sentiment polarity of each aspect from large language models (LLMs) to reduce spurious correlations in ABSA. First, we formulate a prompt template that wraps the sentence, an aspect, and the sentiment label. This template is utilized to prompt LLMs to generate an appropriate explanation that states the sentiment cause. Then, we propose two straightforward yet effective methods to leverage the explanation for preventing the learning of spurious correlations. We conducted extensive comparative experiments on five datasets by integrating them with some representative ABSA models. Results show that our methods can achieve performance gains and enhance the performance and generalization ability of ABSA models.
To avoid detection by current NLP monitoring applications, progenitors of hate speech often replace one or more letters in offensive words with homoglyphs, visually similar Unicode characters. Harvesting real-world hate speech containing homoglyphs is challenging due to the vast replacement possibilities. We developed a character substitution scraping method and assembled the Offensive Tweets with Homoglyphs (OTH) Dataset (N=90,788) with more than 1.5 million occurrences of 1,281 non-Latin characters (emojis excluded). In an annotated sample (n=700), 40.14% of the tweets were found to contain hate speech. We assessed the performance of seven transformer-based hate speech detection models and found that they performed poorly in a zero-shot setting (F1 scores between 0.04 and 0.52) but normalizing the data dramatically improved detection (F1 scores between 0.59 and 0.71). Training the models using the annotated data further boosted performance (highest micro-averaged F1 score=0.88, using five-fold cross validation). This study indicates that a dataset containing homoglyphs known and unknown to the scraping script can be collected, and that neural models can be trained to recognize camouflaged real-world hate speech.
Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enhancing the general proficiency of models. These instructions enable the model to achieve performance comparable to GPT-3.5 on general tasks like open-domain text generation and paraphrasing. However, they fall short of helping the model handle complex reasoning tasks. To bridge the gap, this paper presents LogiCoT, a new instruction-tuning dataset for Logical Chain-of-Thought reasoning with GPT-4. We elaborate on the process of harvesting instructions for prompting GPT-4 to generate chain-of-thought rationales. LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.
Take a Closer Look at Multilinguality! Improve Multilingual Pre-Training Using Monolingual Corpora Only
PDF ↗Recent studies have revealed the remarkable cross-lingual capability of multilingual pre-trained language models (mPLMs), even when pre-trained without parallel corpora (mono-mPLMs). Intuitively, semantic alignments may be the reason behind such capability but remain under-explored. In this work, we investigate the alignment properties from the token perspective in mono-mPLMs and find that the alignments correspond to the geometric similarity of embedding space across different languages. Nevertheless, mono-mPLMs tend to damage this geometric similarity at the higher layers due to the lack of cross-lingual interactions, thus limiting their cross-lingual transfer capabilities. To address this issue, we introduce token-level and semantic-level code-switched masked language modeling, employing the self-induced token alignments to explicitly improve cross-lingual interactions over layers of mono-mPLMs without relying on parallel sentences. We evaluate our method on various natural language understanding tasks and unsupervised machine translation tasks. The results demonstrate that our methods outperform the strong baselines and achieve comparable performance with mPLMs trained with parallel corpora.
Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions
PDF ↗Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question answering (OK-VQA). As images are invisible to LLMs, researchers convert images to text to engage LLMs into the visual question reasoning procedure. This leads to discrepancies between images and their textual representations presented to LLMs, which consequently impedes final reasoning performance. To fill the information gap and better leverage the reasoning capability, we design a framework that enables LLMs to proactively ask relevant questions to unveil more details in the image, along with filters for refining the generated information. We validate our idea on OK-VQA and A-OKVQA. Our method continuously boosts the performance of baselines methods by an average gain of 2.15% on OK-VQA, and achieves consistent improvements across different LLMs.
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values. This alignment requires a vast corpus of human feedback to learn a reward model, which is subsequently used to finetune language models. However, we have identified that the reward model often finds shortcuts to bypass its intended objectives, misleadingly assuming that humans prefer longer responses. The emergence of length bias often induces the model to favor longer outputs, yet it doesn’t equate to an increase in helpful information within these outputs. In this paper, we propose an innovative solution, applying the Product-of-Experts (PoE) technique to separate reward modeling from the influence of sequence length. In our framework, the main expert concentrates on understanding human intents, while the biased expert targets the identification and capture of length bias. To further enhance the learning of bias, we introduce perturbations into the bias-focused expert, disrupting the flow of semantic information. Experimental results validate the effectiveness of our approach, indicating that language model performance is improved, irrespective of sequence length.
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
PDF ↗Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM). By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters and the training cost is much lower than previous work following domain-specific pretraining and finetuning paradigms. Concretely, UReader is jointly finetuned on a wide range of Visually-situated Language Understanding tasks via a unified instruction format. To enhance the visual text and semantic understanding, we further apply two auxiliary tasks with the same format, namely text reading and key points generation tasks. We design a shape-adaptive cropping module before the encoder-decoder architecture of MLLM to leverage the frozen low-resolution vision encoder for processing high-resolution images. Without downstream finetuning, our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks, across 5 domains: documents, tables, charts, natural images, and webpage screenshots. Codes and instruction-tuning datasets will be released.
Cognitive appraisal plays a pivotal role in deciphering emotions. Recent studies have delved into its significance, yet the interplay between various forms of cognitive appraisal and specific emotions, such as joy and anger, remains an area of exploration in consumption contexts. Our research introduces the PEACE-Reviews dataset, a unique compilation of annotated autobiographical accounts where individuals detail their emotional and appraisal experiences during interactions with personally significant products or services. Focusing on the inherent variability in consumer experiences, this dataset offers an in-depth analysis of participants’ psychological traits, their evaluative feedback on purchases, and the resultant emotions. Notably, the PEACE-Reviews dataset encompasses emotion, cognition, individual traits, and demographic data. We also introduce preliminary models that predict certain features based on the autobiographical narratives.