论文检索

Jeonghwan Kim, Giwon Hong, Sung-Hyon Myaeng, Joyce Jiyoung Whang

Compositional reasoning across texts has been a long-standing challenge in natural language processing. With large language models like GPT-4 taking over the field, prompting techniques such as chain-of-thought (CoT) were proposed to unlock compositional, multi-step reasoning capabilities of LLMs. Despite their success, the prompts demand significant human effort to discover and validate them. Our work draws attention to the idea of transferring task-specific inductive biases from finetuned models to prompts, as a way of improving GPT-4’s compositional reasoning capabilities. To leverage these inductive biases, we formulate prompt templates to ease the transfer of inductive biases. The experimental results on multi-hop question answering and numerical reasoning over text show that our proposed prompt scheme shows competitive zero-shot and few-shot performances compared to existing prompts on complicated reasoning tasks, highlighting the importance of adopting the validated biases of the previous paradigm.

Xin Zhou, Yi Lu, Ruotian Ma, Tao Gui, Qi Zhang, Xuanjing Huang

Pre-trained language models (PLMs) are often deployed as cloud services, enabling users to upload textual data and perform inference remotely. However, users’ personal text often contains sensitive information, and sharing such data directly with the service providers can lead to serious privacy leakage. To address this problem, we introduce a novel privacy-preserving inference framework called MixPi , which prevents plaintext leakage during the inference phase. Inspired by k-anonymity, MixPi aims to obfuscate a user’s private input by mixing it with multiple other inputs, thereby confounding potential privacy attackers. To achieve this, our approach involves: (1) proposing a novel encryption module, Privacy Mixer, which encrypts input from three distinct dimensions: mixing, representation, and position. (2) adopting a pre-trained Multi-input Multi-output network to handle mixed representations and obtain multiple predictions. (3) employing a Privacy Demixer to ensure only the user can decrypt the real output among the multiple predictions. Furthermore, we explore different ways to automatically generate synthetic inputs required for mixing. Experimental results on token and sentence classification tasks demonstrate that MixPi greatly surpasses existing privacy-preserving methods in both performance and privacy.

Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng

Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content, including professional documents such as recommendation letters. Though bringing convenience, this application also introduces unprecedented fairness concerns. Model-generated reference letters might be directly used by users in professional scenarios. If underlying biases exist in these model-constructed letters, using them without scrutinization could lead to direct societal harms, such as sabotaging application success rates for female applicants. In light of this pressing issue, it is imminent and necessary to comprehensively study fairness issues and associated harms in this real-world use case. In this paper, we critically examine gender biases in LLM-generated reference letters. Drawing inspiration from social science findings, we design evaluation methods to manifest biases through 2 dimensions: (1) biases in language style and (2) biases in lexical content. We further investigate the extent of bias propagation by analyzing the hallucination bias of models, a term that we define to be bias exacerbation in model-hallucinated contents. Through benchmarking evaluation on 2 popular LLMs- ChatGPT and Alpaca, we reveal significant gender biases in LLM-generated recommendation letters. Our findings not only warn against using LLMs for this application without scrutinization, but also illuminate the importance of thoroughly studying hidden biases and harms in LLM-generated professional documents.

Hongyin Luo, Tianhua Zhang, Yung-Sung Chuang, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, James Glass

Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction learning (SAIL), which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines. With an instruction tuning corpus, we collect search results for each training case from different search APIs and domains, and construct a new search-grounded training set containing (instruction, grounding information, response) triplets. We then fine-tune the LLaMA-7B model on the constructed training set. Since the collected results contain unrelated and disputing languages, the model needs to learn to ground on trustworthy search results, filter out distracting passages, and generate the target response. The search result-denoising process entails explicit trustworthy information selection and multi-hop reasoning, since the retrieved passages might be informative but not contain the instruction-following answer. Experiments show that the fine-tuned SAIL-7B model has a strong instruction-following ability, and it performs significantly better on transparency-sensitive tasks, including open-ended question answering and fact checking.

Manikanta Loya, Divya Sinha, Richard Futrell

The advancement of Large Language Models (LLMs) has led to their widespread use across a broad spectrum of tasks, including decision-making. Prior studies have compared the decision-making abilities of LLMs with those of humans from a psychological perspective. However, these studies have not always properly accounted for the sensitivity of LLMs’ behavior to hyperparameters and variations in the prompt. In this study, we examine LLMs’ performance on the Horizon decision-making task studied by Binz and Schulz (2023), analyzing how LLMs respond to variations in prompts and hyperparameters. By experimenting on three OpenAI language models possessing different capabilities, we observe that the decision-making abilities fluctuate based on the input prompts and temperature settings. Contrary to previous findings, language models display a human-like exploration–exploitation tradeoff after simple adjustments to the prompt.

Sadia Afrin, Md. Shahad Mahmud Chowdhury, Md. Islam, Faisal Khan, Labib Chowdhury, Md. Mahtab, Nazifa Chowdhury, Massud Forkan, Neelima Kundu, Hakim Arif 等

Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning. However, due to the highly inflected nature and morphological richness, lemmatization in Bangla text poses a complex challenge. In this study, we propose linguistic rules for lemmatization and utilize a dictionary along with the rules to design a lemmatizer specifically for Bangla. Our system aims to lemmatize words based on their parts of speech class within a given sentence. Unlike previous rule-based approaches, we analyzed the suffix marker occurrence according to the morpho-syntactic values and then utilized sequences of suffix markers instead of entire suffixes. To develop our rules, we analyze a large corpus of Bangla text from various domains, sources, and time periods to observe the word formation of inflected words. The lemmatizer achieves an accuracy of 96.36% when tested against a manually annotated test dataset by trained linguists and demonstrates competitive performance on three previously published Bangla lemmatization datasets. We are making the code and datasets publicly available at https://github.com/eblict-gigatech/BanLemma in order to contribute to the further advancement of Bangla NLP.

Chenxi Gu, Xiaoqing Zheng, Jianhan Xu, Muling Wu, Cenyuan Zhang, Chengsong Huang, Hua Cai, Xuanjing Huang

Large pre-trained language models (PLMs) have achieved remarkable success, making them highly valuable intellectual property due to their expensive training costs. Consequently, model watermarking, a method developed to protect the intellectual property of neural models, has emerged as a crucial yet underexplored technique. The problem of watermarking PLMs has remained unsolved since the parameters of PLMs will be updated when fine-tuned on downstream datasets, and then embedded watermarks could be removed easily due to the catastrophic forgetting phenomenon. This study investigates the feasibility of watermarking PLMs by embedding backdoors that can be triggered by specific inputs. We employ contrastive learning during the watermarking phase, allowing the representations of specific inputs to be isolated from others and mapped to a particular label after fine-tuning. Moreover, we demonstrate that by combining weight perturbation with the proposed method, watermarks can be embedded in a flatter region of the loss landscape, thereby increasing their robustness to watermark removal. Extensive experiments on multiple datasets demonstrate that the embedded watermarks can be robustly extracted without any knowledge about downstream tasks, and with a high success rate.

Morteza Rohanian, Farhad Nooralahzadeh, Omid Rohanian, David Clifton, Michael Krauthammer

In computational linguistics, the common practice is to “clean” disfluent content from spontaneous speech. However, we hypothesize that these disfluencies might serve as more than mere noise, potentially acting as informative cues. We use a range of pre-trained models for a reading comprehension task involving disfluent queries, specifically featuring different types of speech repairs. The findings indicate that certain disfluencies can indeed improve model performance, particularly those stemming from context-based adjustments. However, large-scale language models struggle to handle repairs involving decision-making or the correction of lexical or syntactic errors, suggesting a crucial area for potential improvement. This paper thus highlights the importance of a nuanced approach to disfluencies, advocating for their potential utility in enhancing model performance rather than their removal.

Sanne Hoeken, Özge Alacam, Antske Fokkens, Pia Sommerauer

In this paper, we investigate automatic detection of subtle semantic shifts between social communities of different political convictions in Dutch and English. We perform a methodological study comparing methods using static and contextualized language models. We investigate the impact of specializing contextualized models through fine-tuning on target corpora, word sense disambiguation and sentiment. We furthermore propose a new approach using masked token prediction, that relies on behavioral information, specifically the most probable substitutions, instead of geometrical comparison of representations. Our results show that methods using static models and our masked token prediction method can detect differences in connotation of politically loaded terms, whereas methods that rely on measuring the distance between contextualized representations are not providing clear signals, even in synthetic scenarios of extreme shifts.

Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui

Factual probing is a method that uses prompts to test if a language model “knows” certain world knowledge facts. A problem in factual probing is that small changes to the prompt can lead to large changes in model output. Previous work aimed to alleviate this problem by optimizing prompts via text mining or fine-tuning. However, such approaches are relation-specific and do not generalize to unseen relation types. Here, we propose to use test-time augmentation (TTA) as a relation-agnostic method for reducing sensitivity to prompt variations by automatically augmenting and ensembling prompts at test time. Experiments show improved model calibration, i.e., with TTA, model confidence better reflects prediction accuracy. Improvements in prediction accuracy are observed for some models, but for other models, TTA leads to degradation. Error analysis identifies the difficulty of producing high-quality prompt variations as the main challenge for TTA.

Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy Nguyen, See-Kiong Ng, Anh Luu

Temporal Language Grounding seeks to localize video moments that semantically correspond to a natural language query. Recent advances employ the attention mechanism to learn the relations between video moments and the text query. However, naive attention might not be able to appropriately capture such relations, resulting in ineffective distributions where target video moments are difficult to separate from the remaining ones. To resolve the issue, we propose an energy-based model framework to explicitly learn moment-query distributions. Moreover, we propose DemaFormer, a novel Transformer-based architecture that utilizes exponential moving average with a learnable damping factor to effectively encode moment-query inputs. Comprehensive experiments on four public temporal language grounding datasets showcase the superiority of our methods over the state-of-the-art baselines.

Xiaoyi Bao, Zhongqing Wang, Guodong Zhou

Existing studies tend to extract the sentiment elements in a generative manner in order to avoid complex modeling. Despite their effectiveness, they ignore importance of the relationships between sentiment elements that could be crucial, making the large pre-trained generative models sub-optimal for modeling sentiment knowledge. Therefore, we introduce two pre-training paradigms to improve the generation model by exploring graph pre-training that targeting to strengthen the model in capturing the elements’ relationships. Specifically, We first employ an Element-level Graph Pre-training paradigm, which is designed to improve the structure awareness of the generative model. Then, we design a Task Decomposition Pre-training paradigm to make the generative model generalizable and robust against various irregular sentiment quadruples. Extensive experiments show the superiority of our proposed method, validate the correctness of our motivation.

Xi Wang, Hossein Rahmani, Jiqun Liu, Emine Yilmaz

Conversational Recommendation System (CRS) is a rapidly growing research area that has gained significant attention alongside advancements in language modelling techniques. However, the current state of conversational recommendation faces numerous challenges due to its relative novelty and limited existing contributions. In this study, we delve into benchmark datasets for developing CRS models and address potential biases arising from the feedback loop inherent in multi-turn interactions, including selection bias and multiple popularity bias variants. Drawing inspiration from the success of generative data via using language models and data augmentation techniques, we present two novel strategies, ‘Once-Aug’ and ‘PopNudge’, to enhance model performance while mitigating biases. Through extensive experiments on ReDial and TG-ReDial benchmark datasets, we show a consistent improvement of CRS techniques with our data augmentation approaches and offer additional insights on addressing multiple newly formulated biases.

Zheye Deng, Weiqi Wang, Zhaowei Wang, Xin Liu, Yangqiu Song

Commonsense Knowledge Graphs (CSKGs) are crucial for commonsense reasoning, yet constructing them through human annotations can be costly. As a result, various automatic methods have been proposed to construct CSKG with larger semantic coverage. However, these unsupervised approaches introduce spurious noise that can lower the quality of the resulting CSKG, which cannot be tackled easily by existing denoising algorithms due to the unique characteristics of nodes and structures in CSKGs. To address this issue, we propose Gold (Global and Local-aware Denoising), a denoising framework for CSKGs that incorporates entity semantic information, global rules, and local structural information from the CSKG. Experiment results demonstrate that Gold outperforms all baseline methods in noise detection tasks on synthetic noisy CSKG benchmarks. Furthermore, we show that denoising a real-world CSKG is effective and even benefits the downstream zero-shot commonsense question-answering task. Our code and data are publicly available at https://github.com/HKUST-KnowComp/GOLD.

Xiaohang Tang, Yi Zhou, Taichi Aida, Procheta Sen, Danushka Bollegala

Semantic Change Detection of words is an important task for various NLP applications that must make time-sensitive predictions. Some words are used over time in novel ways to express new meanings, and these new meanings establish themselves as novel senses of existing words. On the other hand, Word Sense Disambiguation (WSD) methods associate ambiguous words with sense ids, depending on the context in which they occur. Given this relationship between WSD and SCD, we explore the possibility of predicting whether a target word has its meaning changed between two corpora collected at different time steps, by comparing the distributions of senses of that word in each corpora. For this purpose, we use pretrained static sense embeddings to automatically annotate each occurrence of the target word in a corpus with a sense id. Next, we compute the distribution of sense ids of a target word in a given corpus. Finally, we use different divergence or distance measures to quantify the semantic change of the target word across the two given corpora. Our experimental results on SemEval 2020 Task 1 dataset show that word sense distributions can be accurately used to predict semantic changes of words in English, German, Swedish and Latin.

Liwen Hou, David Smith

We investigate the ability of Transformer-based language models to find syntactic differences between the English of the early 1800s and that of the late 1900s. First, we show that a fine-tuned BERT model can distinguish between text from these two periods using syntactic information only; to show this, we employ a strategy to hide semantic information from the text. Second, we make further use of fine-tuned BERT models to identify specific instances of syntactic change and specific words for which a new part of speech was introduced. To do this, we employ an automatic part-of-speech (POS) tagger and use it to train corpora-specific taggers based only on BERT representations pretrained on different corpora. Notably, our methods of identifying specific candidates for syntactic change avoid using any automatic POS tagger on old text, where its performance may be unreliable; instead, our methods only use untagged old text together with tagged modern text. We examine samples and distributional properties of the model output to validate automatically identified cases of syntactic change. Finally, we use our techniques to confirm the historical rise of the progressive construction, a known example of syntactic change.

Martin Vejvar, Yasutaka Fujimoto

We present ASPIRO, an approach for structured data verbalisation into short template sentences in zero to few-shot settings. Unlike previous methods, our approach prompts Large Language Models (LLMs) to directly produce entity-agnostic templates, rather than relying on LLMs to faithfully copy the given example entities, or validating/crafting the templates manually. We incorporate LLM re-prompting, triggered by algorithmic parsing checks, as well as the PARENT metric induced consistency validation to identify and rectify template generation problems in real-time. ASPIRO, compared to direct LLM output, averages 66% parsing error rate reduction in generated verbalisations of RDF triples on the DART dataset. Our best 5-shot text-davinci-003 setup, scoring BLEU of 50.62, METEOR of 45.16, BLEURT of 0.82, NUBIA of 0.87, and PARENT of 0.8962 on the Rel2Text dataset, competes effectively with recent fine-tuned pretrained language models.

Ayan Sengupta, Md. Shad Akhtar, Tanmoy Chakraborty

Multi-head self-attention-based Transformers have shown promise in different learning tasks. Albeit these models exhibit significant improvement in understanding short-term and long-term contexts from sequences, encoders of Transformers and their variants fail to preserve layer-wise contextual information. Transformers usually project tokens onto sparse manifolds and fail to preserve mathematical equivalence among the token representations. In this work, we propose TransJect, an encoder model that guarantees a theoretical bound for layer-wise distance preservation between a pair of tokens. We propose a simple alternative to dot-product attention to ensure Lipschitz continuity. This allows TransJect to learn injective mappings to transform token representations to different manifolds with similar topology and preserve Euclidean distance between every pair of tokens in subsequent layers. Evaluations across multiple benchmark short- and long-sequence classification tasks show maximum improvements of 6.8% and 5.9%, respectively, over the variants of Transformers. Additionally, TransJect displays 79% better performance than Transformer on the language modeling task. We further highlight the shortcomings of multi-head self-attention from the statistical physics viewpoint. Although multi-head self-attention was incepted to learn different abstraction levels within the networks, our empirical analyses suggest that different attention heads learn randomly and unorderly. In contrast, TransJect adapts a mixture of experts for regularization; these experts are more orderly and balanced and learn different sparse representations from the input sequences. TransJect exhibits very low entropy and can be efficiently scaled to larger depths.

Hanchong Zhang, Ruisheng Cao, Lu Chen, Hongshen Xu, Kai Yu

Recently Large Language Models (LLMs) have been proven to have strong abilities in various domains and tasks. We study the problem of prompt designing in the text-to-SQL task and attempt to improve the LLMs’ reasoning ability when generating SQL queries. Besides the trivial few-shot in-context learning setting, we design our chain-of-thought (CoT) prompt with a similar method to schema linking. We provide a method named ACT-SQL to automatically generate auto-CoT exemplars and thus the whole process doesn’t need manual labeling. Our approach is cost-saving since we only use the LLMs’ API call once when generating one SQL query. Furthermore, we extend our in-context learning method to the multi-turn text-to-SQL task. The experiment results show that the LLMs’ performance can benefit from our ACT-SQL approach. Our approach achieves SOTA performance on the Spider dev set among existing in-context learning approaches.

Gabriel Sarch, Yue Wu, Michael Tarr, Katerina Fragkiadaki

Pre-trained and frozen LLMs can effectively map simple scene re-arrangement instructions to programs over a robot’s visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural language and adapt to a user’s idiosyncratic procedures, not known during prompt engineering time, fixed prompts fall short. In this paper, we introduce HELPER, an embodied agent equipped with an external memory of language-program pairs that parses free-form human-robot dialogue into action programs through retrieval-augmented LLM prompting: relevant memories are retrieved based on the current dialogue, instruction, correction or VLM description, and used as in-context prompt examples for LLM querying. The memory is expanded during deployment to include pairs of user’s language and action plans, to assist future inferences and personalize them to the user’s language and routines. HELPER sets a new state-of-the-art in the TEACh benchmark in both Execution from Dialog History (EDH) and Trajectory from Dialogue (TfD), with 1.7x improvement over the previous SOTA for TfD. Our models, code and video results can be found in our project’s website: https://helper-agent-llm.github.io.