论文检索

Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Tongshuang Wu, Jianshu Chen

For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance. While it is now common sense that LLM performances are greatly impacted by prompts, the confidence calibration in prompting LLMs has yet to be thoroughly explored.In this paper, we explore how different prompting strategies influence LLM confidence calibration and how it could be improved. We conduct extensive experiments on six prompting methods in the question-answering context and we observe that, while these methods help improve the expected LLM calibration, they also trigger LLMs to be over-confident when responding to some instances.Inspired by human cognition, we propose Fact-and-Reflection (FaR) prompting, which improves the LLM calibration in two steps. First, FaR elicits the known “facts” that are relevant to the input prompt from the LLM. And then it asks the model to “reflect” over them to generate the final answer.Experiments show that FaR prompting achieves significantly better calibration; it lowers the Expected Calibration Error by 23.5% on our multi-purpose QA tasks. Notably, FaR prompting even elicits the capability of verbally expressing concerns in less confident scenarios, which helps trigger retrieval augmentation for solving these harder instances.

Yiduo Guo, Zekai Zhang, Yaobo Liang, Dongyan Zhao, Nan Duan

Recent evaluations of Large Language Models (LLMs) have centered around testing their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translate instructions into tool APIs. However, the evaluation of LLMs utilizing complex tools to finish multi-turn, multi-modal instructions in a complex multi-modal environment has not been investigated. To address this gap, we introduce the PowerPoint Task Completion (PPTC) benchmark to assess LLMs’ ability to create and edit PPT files based on user instructions. It contains 279 multi-turn sessions covering diverse topics and hundreds of instructions involving multi-modal operations. We also propose the PPTX-Match Evaluation System that evaluates if LLMs finish the instruction based on the prediction file rather than the label API sequence, thus it supports various LLM-generated API sequences. We measure 3 closed LLMs and 6 open-source LLMs. The results show that GPT-4 outperforms other LLMs with 75.1% accuracy in single-turn dialogue testing but faces challenges in completing entire sessions, achieving just 6% session accuracy. We find three main error causes in our benchmark: error accumulation in the multi-turn session, long PPT template processing, and multi-modality perception. These pose great challenges for future LLM and agent systems .

Zhenyi Wang, Haiyan Ning, Qing Ling, Dan Wang

Text embedding requires a highly efficient method for training domain-specific models on limited data, as general models trained on large corpora lack universal applicability in highly specific fields. Therefore, we have introduced VAEGPT-Sim, an innovative model for generating synonyms that combines a denoising variational autoencoder with a target-specific discriminator to generate synonymous sentences that closely resemble human language. Even when trained with completely unsupervised settings, it maintains a harmonious balance between semantic similarity and lexical diversity, as shown by a comprehensive evaluation metric system with the highest average scores compared to other generative models. When VAEGPT-Sim is utilized as a module for contrastive learning in text representation, it delivers state-of-the-art results in small-dataset training on STS benchmarks, surpassing ConSERT by 2.8 points. This approach optimizes the effectiveness of text representation despite a limited corpus, signifying an advancement in domain-specific embedding technology.

Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu 等

Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data by utilizing a few labeled data with only known categories. Due to the lack of supervision and category information, current methods usually perform poorly on novel categories and struggle to reveal semantic meanings of the discovered clusters, which limits their applications in the real world. To mitigate the above issues, we propose Loop, an end-to-end active-learning framework that introduces Large Language Models (LLMs) into the training loop, which can boost model performance and generate category names without relying on any human efforts. Specifically, we first propose Local Inconsistent Sampling (LIS) to select samples that have a higher probability of falling to wrong clusters, based on neighborhood prediction consistency and entropy of cluster assignment probabilities. Then we propose a Scalable Query strategy to allow LLMs to choose true neighbors of the selected samples from multiple candidate samples. Based on the feedback from LLMs, we perform Refined Neighborhood Contrastive Learning (RNCL) to pull samples and their neighbors closer to learn clustering-friendly representations. Finally, we select representative samples from clusters corresponding to novel categories to allow LLMs to generate category names for them. Extensive experiments on three benchmark datasets show that Loop outperforms SOTA models by a large margin and generates accurate category names for the discovered clusters. Code and data are available at https://github.com/Lackel/LOOP.

Hyuk Namgoong, Jeesu Jung, Sangkeun Jung, YoonHyung Roh

Recent advancements in large language models have heavily relied on the large reward model from reinforcement learning from human feedback for fine-tuning. However, the use of a single reward model across various domains may not always be optimal, often requiring retraining from scratch when new domain data is introduced. To address these challenges, we explore the utilization of small language models operating in a domain-specific manner based on router mechanisms. Our three approaches are: 1) utilize mixture of experts to form a single reward model by modularizing an internal router and experts, 2) employing external router to select the appropriate reward model from multiple domain-specific models, and 3) the framework reduces parameter size by loading reward models and router adapters onto a single small language model using adapters. Experimental validation underscores the effectiveness of our approach, demonstrating performance comparable to baseline methods while also reducing the total parameter size.

Tao Zhang, Chenwei Zhang, Xian Li, Jingbo Shang, Hoang Nguyen, Philip Yu

Attribute value extraction involves identifying the value spans of predetermined attributes in product texts. This area of research has traditionally operated under a closed-world assumption, focusing on products from a static set of categories and their associated attributes. However, products in e-commerce stores are ever-increasing and evolving, calling for life-long learning. If continuously trained on the fast-increasing products and attributes, most existing solutions not only struggle for parameter efficiency but also endure foreseeable defects due to data contamination, catastrophic forgetting, etc. As a remedy, we propose and study a new task, which aims to effectively maintain a strong single model for many domains in a life-long learning fashion, without jeopardizing the model performance and parameter efficiency. We introduce factorization into the model and make it domain-aware by decoupling the modeling of product type and attribute, as a way to promote de-contamination and parameter efficiency while scaling up. Tuning the model with distillation prevents forgetting historical knowledge and enables continuous learning from emerging domains. Experiments on hundreds of domains showed that our model attains the near state-of-the-art performance with affordable parameter size, the least historical knowledge forgetting, and the greatest robustness against noises, whilst adding only a few parameters per domain when compared with competitive baselines.

Guangqian Yang, Yi Liu, Lei Zhang, Licheng Zhang, Hongtao Xie, Zhendong Mao

Text-based knowledge graph completion (KGC) methods utilize pre-trained language models for triple encoding and further fine-tune the model to achieve completion. Despite their excellent performance, they neglect the knowledge context in inferring process. Intuitively, knowledge contexts, which refer to the neighboring triples around the target triples, are important information for triple inferring, since they provide additional detailed information about the entities. To this end, we propose a novel framework named KnowC, which models the knowledge context as additional prompts with pre-trained language models for knowledge graph completion. Given the substantial number of neighbors typically associated with entities, along with the constrained input token capacity of language models, we further devise several strategies to sample the neighbors. We conduct extensive experiments on common datasets FB15k-237, WN18RR and Wikidata5M, experiments show that KnowC achieves state-of-the-art performance.

Marcio Fonseca, Shay B. Cohen

In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries such as paper reviews, abstracts, and lay summaries. By controlling stylistic features, we find that non-fine-tuned LLMs outperform humans in the MuP review generation task, both in terms of similarity to reference summaries and human preferences. Also, we show that we can improve the controllability of LLMs with keyword-based classifier-free guidance (CFG) while achieving lexical overlap comparable to strong fine-tuned baselines on arXiv and PubMed. However, our results also indicate that LLMs cannot consistently generate long summaries with more than 8 sentences. Furthermore, these models exhibit limited capacity to produce highly abstractive lay summaries. Although LLMs demonstrate strong generic summarization competency, sophisticated content control without costly fine-tuning remains an open problem for domain-specific applications.

Shuqi Liu, Bowei He, Linqi Song

Large Language Models (LLMs) have shown human-like reasoning abilities but still face challenges in solving complex logical problems. Existing unidirectional chaining methods, such as forward chaining and backward chaining, suffer from issues like low prediction accuracy and efficiency. To address these, we propose a bidirectional chaining method, Bi-Chainer, which dynamically switches to depth-first reasoning in the opposite reasoning direction when it encounters multiple branching options within the current direction. Thus, the intermediate reasoning results can be utilized as guidance to facilitate the reasoning process. We show that Bi-Chainer achieves sizable accuracy boots over unidirectional chaining frameworks on four challenging logical reasoning datasets. Moreover, Bi-Chainer enhances the accuracy of intermediate proof steps and reduces the average number of inference calls, resulting in more efficient and accurate reasoning.

Masashi Oshika, Makoto Morishita, Tsutomu Hirao, Ryohei Sasano, Koichi Takeda

In recent years, neural machine translation (NMT) has become widely used in everyday life. However, the current NMT lacks a mechanism to adjust the difficulty level of translations to match the user’s language level. Additionally, due to the bias in the training data for NMT, translations of simple source sentences are often produced with complex words. In particular, this could pose a problem for children, who may not be able to understand the meaning of the translations correctly. In this study, we propose a method that replaces high Age of Acquisitions (AoA) words in translations with simpler words to match the translations to the user’s level. We achieve this by using large language models (LLMs), providing a triple of a source sentence, a translation, and a target word to be replaced. We create a benchmark dataset using back-translation on Simple English Wikipedia. The experimental results obtained from the dataset show that our method effectively replaces high-AoA words with lower-AoA words and, moreover, can iteratively replace most of the high-AoA words while still maintaining high BLEU and COMET scores.

Yuu Jinnai, Kaito Ariu

Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks. However, MBR requires a huge amount of time for inference to compute the MBR objective, which makes the method infeasible in many situations where response time is critical. Confidence-based pruning (CBP) (Cheng and Vlachos, 2023) has recently been proposed to reduce the inference time in machine translation tasks. Although it is shown to significantly reduce the amount of computation, it requires hyperparameter tuning using a development set to be effective. To this end, we propose Adaptive Minimum Bayes-Risk (AMBR) decoding, a hyperparameter-free method to run MBR decoding efficiently. AMBR is derived from the observation that the problem of computing the sample-based MBR objective is the medoid identification problem. AMBR uses the Correlated Sequential Halving (CSH) algorithm (Baharav and Tse, 2019), the algorithm with the best performance guarantee to date for the medoid identification problem, to compute the sample-based MBR objective. We evaluate AMBR on machine translation, text summarization, and image captioning tasks. The results show that AMBR achieves on par with CBP, with CBP selecting hyperparameters through an Oracle for each given computation budget.

Spencer Rarrick, Ranjita Naik, Sundar Poudel, Vishal Chowdhary

Neural Machine Translation (NMT) continues to improve in quality and adoption, yet the in advertent perpetuation of gender bias remains a significant concern. Despite numerous studies on gender bias in translations into English from weakly gendered-languages, there are no benchmarks for evaluating this phenomenon or for assessing mitigation strategies. To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English. Each translation is accompanied by feminine, masculine, and neutral variants. The dataset, which contains between 1250 and 1850 instances for each of the four language pairs, features natural sentences with a wide range of sentence lengths and domains, challenging translation rewriters on various linguistic phenomena. Additionally, we present a translation gender rewriting solution built with GPT-4 and use GATE X-E to evaluate it. We open source our contributions to encourage further research on gender debiasing.

Yuu Jinnai, Ukyo Honda, Tetsuro Morimura, Peinan Zhang

One of the most important challenges in text generation systems is to produce outputs that are not only correct but also diverse.Recently, Minimum Bayes-Risk (MBR) decoding has gained prominence for generating sentences of the highest quality among the decoding algorithms. However, existing algorithms proposed to generate diverse outputs are predominantly based on beam search or random sampling, thus their output quality is capped by these underlying decoding algorithms. In this paper, we investigate an alternative approach – we develop diversity-promoting decoding algorithms by enforcing diversity objectives to MBR decoding.We propose two variants of MBR; (i) Diverse MBR (DMBR) that adds a diversity penalty to the decoding objective and (ii) k-medoids MBR (KMBR) that reformulates the decoding task as a clustering problem.We evaluate DMBR and KMBR on a variety of directed text generation tasks using encoder-decoder models and a language model with prompting. The experimental results show that the proposed method achieves a better trade-off than the diverse beam search and sampling algorithms overall.

Xuanming Zhang, Zixun Chen, Zhou Yu

Lexical Substitution discovers appropriate substitutes for a given target word in a context sentence. However, the task fails to consider substitutes that are of equal or higher proficiency than the target, an aspect that could be beneficial for language learners looking to improve their writing. To bridge this gap, we propose a new task — language proficiency-oriented lexical substitution. We also introduce ProLex, a novel benchmark designed to assess systems’ ability to generate not only appropriate substitutes but also substitutes that demonstrate better language proficiency. Besides the benchmark, we propose models that can automatically perform the new task. We show that our best model, a Llama2-13B model fine-tuned with task-specific synthetic data, outperforms ChatGPT by an average of 3.2% in F-score and achieves comparable results with GPT-4 on ProLex.

Hannah McLean Babe, Sydney Nguyen, Yangtian Zi, Arjun Guha, Molly Q Feldman, Carolyn Jane Anderson

Code LLMs have the potential to make it easier for non-experts to understand and write code. However, current CodeLLM benchmarks rely on a single expert-written prompt per problem, making it hard to generalize their success to non-expert users. In this paper, we present a new natural-language-to-code benchmark of prompts written by a key population of non-experts: beginning programmers. StudentEval contains 1,749 prompts written by 80 students who have only completed one introductory Python course. StudentEval contains numerous non-expert prompts describing the same problem, enabling exploration of key factors in prompt success. We use StudentEval to evaluate 12 Code LLMs and find that StudentEval is a better discriminator of model performance than existing benchmarks. Our analysis of student prompting strategies reveals that nondeterministic LLM sampling can mislead students about the quality of their descriptions, a finding with key implications for Code LLMs in education.

Wanqiu Long, N. Siddharth, Bonnie Webber

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in this domain. In PDTB-3, the annotators can assign multiple labels to an example, when they believe the simultaneous presence of multiple relations. Prior research in discourse relation recognition has treated these instances as separate examples during training, with a gold-standard prediction matching one of the labels considered correct at test time. However, this approach is inadequate, as it fails to account for the interdependence of labels in real-world contexts and to distinguish between cases where only one sense relation holds and cases where multiple relations hold simultaneously. In our work, we address this challenge by exploring various multi-label classification frameworks to handle implicit discourse relation recognition. We show that the methods for multi-label prediction don’t depress performance for single-label prediction. Additionally, we give comprehensive analysis of results and data. Our work contributes to advancing the understanding and application of discourse relations and provide a foundation for the future study.

Ante Wang, Linfeng Song, Baolin Peng, Lifeng Jin, Ye Tian, Haitao Mi, Jinsong Su, Dong Yu

This work studies mitigating fact-conflicting hallucinations for large language model (LLM) at inference time.Particularly, we propose a self-endorsement framework that leverages the fine-grained fact-level comparisons across multiple sampled responses.Compared with prior ensemble methods (e.g., self-consistency) that perform response-level selection, our approach can better alleviate hallucinations for knowledge-intensive tasks.Our approach can broadly benefit smaller and open-source LLMs as it mainly conducts simple content-based comparisons.Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.Besides, comprehensive analyses on TriviaQA and GSM8K demonstrate the potential of self-endorsement for broader application.

Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch

Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions. A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training. This approach not only incurs high cost, but also results in poorly translated data due to the non-standard formatting of mathematical chain-of-thought. In this paper, we explore the benefits of question alignment, where we train the model to translate reasoning questions into English by finetuning on X-English parallel question data. In this way we perform targeted, in-domain language alignment which makes best use of English instruction data to unlock the LLMs’ multilingual reasoning abilities. Experimental results on LLaMA2-13B show that question alignment leads to consistent improvements over the translate-training approach: an average improvement of 11.3% and 16.1% accuracy across ten languages on the MGSM and MSVAMP multilingual reasoning benchmarks.

Ishan Agrawal, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Mrinmaya Sachan, Bernhard Schölkopf

Citation count of a paper is a commonly used proxy for evaluating the significance of a paper in the scientific community. Yet citation measures are widely criticized for failing to accurately reflect the true impact of a paper. Thus, we propose CausalCite, a new way to measure the significance of a paper by assessing the causal impact of the paper on its follow-up papers. CausalCite is based on a novel causal inference method, TextMatch, which adapts the traditional matching framework to high-dimensional text embeddings. TextMatch encodes each paper using text embeddings from large language models (LLMs), extracts similar samples by cosine similarity, and synthesizes a counterfactual sample as the weighted average of similar papers according to their similarity values. We demonstrate the effectiveness of CausalCite on various criteria, such as high correlation with paper impact as reported by scientific experts on a previous dataset of 1K papers, (test-of-time) awards for past papers, and its stability across various subfields of AI. We also provide a set of findings that can serve as suggested ways for future researchers to use our metric for a better understanding of the quality of a paper. Our code is available at https://github.com/causalNLP/causal-cite.

Fabrice Lamarche, Philippe Langlais

Open Information Extraction (OIE) is a field of natural language processing that aims to present textual information in a format that allows it to be organized, analyzed and reflected upon. Numerous OIE systems are developed, claiming ever-increasing performance, marking the need for objective benchmarks. BenchIE is the latest reference we know of. Despite being very well thought out, we noticed a number of issues we believe are limiting. Therefore, we propose BenchIE^FL, a new OIE benchmark which fully enforces the principles of BenchIE while containing fewer errors, omissions and shortcomings when candidate facts are matched towards reference ones. BenchIE^FL allows insightful conclusions to be drawn on the actual performance of OIE extractors.