论文检索

Zeyu Liu, Souvik Kundu, Anni Li, Junrui Wan, Lianghao Jiang, Peter Beerel

We present a novel Parameter-Efficient Fine-Tuning (PEFT) method, dubbed as \textit{Adaptive Freezing of Low-Rank Adaptation} (AFLoRA). Specifically, for each pre-trained frozen weight tensor, we add a parallel path of trainable low-rank matrices, namely a down-projection and an up-projection matrix, each of which is followed by a feature transformation vector. Based on a novel freezing score, we incrementally freeze these projection matrices during fine-tuning to reduce the computation and alleviate over-fitting. Our experimental results demonstrate that we can achieve state-of-the-art performance with an average improvement of up to 0.85% as evaluated on the GLUE benchmark while yielding up to 9.5\times fewer average trainable parameters. While compared in terms of runtime, AFLoRA can yield up to 1.86\times improvement as opposed to similar PEFT alternatives. Besides the practical utility of our approach, we provide insights on the trainability requirements of LoRA paths at different modules and the freezing schedule for the different projection matrices.

Zhihong Zhu, Xuxin Cheng, Zhanpeng Chen, Xianwei Zhuang, Zhiqi Huang, Yuexian Zou

Zero-shot cross-lingual spoken language understanding (SLU) can promote the globalization application of dialog systems, which has attracted increasing attention. While current code-switching based cross-lingual SLU frameworks have shown promising results, they (i) predominantly utilize contrastive objectives to model hard alignment, which may disrupt the inherent structure within sentences of each language; and (ii) focus optimization objectives solely on the original sentences, neglecting the relation between original sentences and code-switched sentences, which may hinder contextualized embeddings from further alignment. In this paper, we propose a novel framework dubbed REPE (short for Representation-Level and Prediction-Level Alignment), which leverages both code-switched and original sentences to achieve multi-level alignment. Specifically, REPE introduces optimal transport to facilitate soft alignment between the representations of code-switched and original sentences, thereby preserving structural integrity as much as possible. Moreover, REPE adopts multi-view learning to enforce consistency regularization between the prediction of the two sentences, aligning them into a more refined language-invariant space. Based on this, we further incorporate a self-distillation layer to boost the robustness of REPE. Extensive experiments on two benchmarks across ten languages demonstrate the superiority of the proposed REPE framework.

Haowei Du, Chen Li, Dinghao Zhang, Dongyan Zhao

The knowledge graph-to-text (KG-to-text) generation task aims to synthesize coherent and engaging sentences that accurately convey the complex information derived from an input knowledge graph. Existing methods generate the whole target text based on all KG triples at once and may incorporate incorrect KG triples for each sentence. To this end, we propose the bi-directional multi-granularity generation framework. Instead of generating the whole text at a time, we construct the sentence level generation based on the corresponding triples and generate the graph-level text as a result. Moreover, we design a backward relation extraction task to enhance the correctness of relational information. Our method achieves the new state-of-the-art in benchmark dataset WebNLG and further analysis shows the efficiency of different modules.

Honghao Gui, Lin Yuan, Hongbin Ye, Ningyu Zhang, Mengshu Sun, Lei Liang, Huajun Chen

Large Language Models (LLMs) demonstrate remarkable potential across various domains; however, they exhibit a significant performance gap in Information Extraction (IE). Note that high-quality instruction data is the vital key for enhancing the specific capabilities of LLMs, while current IE datasets tend to be small in scale, fragmented, and lack standardized schema. To this end, we introduce IEPile, a comprehensive bilingual (English and Chinese) IE instruction corpus, which contains approximately 0.32B tokens. We construct IEPile by collecting and cleaning 33 existing IE datasets, and introduce schema-based instruction generation to unearth a large-scale corpus. Experimentally, IEPile enhance the performance of LLMs for IE, with notable improvements in zero-shot generalization. We open-source the resource and pre-trained models, hoping to provide valuable support to the NLP community.

Dongyang Li, Junbing Yan, Taolin Zhang, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang

Retrieval augmented generation (RAG) exhibits outstanding performance in promoting the knowledge capabilities of large language models (LLMs) with retrieved documents related to user queries. However, RAG only focuses on improving the response quality of LLMs via enhancing queries indiscriminately with retrieved information, paying little attention to what type of knowledge LLMs really need to answer original queries more accurately. In this paper, we suggest that long-tail knowledge is crucial for RAG as LLMs have already remembered common world knowledge during large-scale pre-training. Based on our observation, we propose a simple but effective long-tail knowledge detection method for LLMs. Specifically, the novel Generative Expected Calibration Error (GECE) metric is derived to measure the “long-tailness” of knowledge based on both statistics and semantics. Hence, we retrieve relevant documents and infuse them into the model for patching knowledge loopholes only when the input query relates to long-tail knowledge. Experiments show that, compared to existing RAG pipelines, our method achieves over 4x speedup in average inference time and consistent performance improvement in downstream tasks.

Zhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou, Tianyu Yang, Jiajun Jiao, Renjie Pi, Jipeng Zhang, Xiangliang Zhang

The paper introduces SceMQA, a novel benchmark for scientific multimodal question answering at the college entrance level. It addresses a critical educational phase often overlooked in existing benchmarks, spanning high school to pre-college levels. SceMQA focuses on core science subjects including Mathematics, Physics, Chemistry, and Biology. It features a blend of multiple-choice and free-response formats, ensuring a comprehensive evaluation of AI models’ abilities. Additionally, our benchmark provides specific knowledge points for each problem and detailed explanations for each answer. SceMQA also uniquely presents problems with identical contexts but varied questions to facilitate a more thorough and accurate assessment of reasoning capabilities. In the experiment, we evaluate both open-source and close-source state-of-the-art Multimodal Large Language Models (MLLMs), across various experimental settings. The results show that further research and development are needed in developing more capable MLLM, as highlighted by only 50% to 60% accuracy achieved by the strongest models.

Peter Belcak, Roger Wattenhofer

We present UltraSparseBERT, a BERT variant that uses 0.3% of its neurons during inference while performing on par with similar BERT models. UltraSparseBERT selectively engages just 12 out of 4095 neurons for each layer inference. This is achieved by reorganizing feedforward networks into fast feedforward networks (FFFs).To showcase but one benefit of high sparsity, we provide an Intel MKL implementation achieving 78x speedup over the optimized feedforward baseline on CPUs, and an OpenAI Triton implementation performing forward passes 4.1x faster than the corresponding native GPU implementation. The training and benchmarking code is enclosed.

Zheng Wei Lim, Ekaterina Vylomova, Trevor Cohn, Charles Kemp

A good translation should be faithful to the source and should respect the norms of the target language. We address a theoretical puzzle about the relationship between these objectives. On one hand, intuition and some prior work suggest that accuracy and fluency should trade off against each other, and that capturing every detail of the source can only be achieved at the cost of fluency. On the other hand, quality assessment researchers often suggest that accuracy and fluency are highly correlated and difficult for human raters to distinguish (Callison-Burch et al., 2007). We show that the tension between these views is an instance of Simpson’s paradox, and that accuracy and fluency are positively correlated at the level of the corpus but trade off at the level of individual source segments. We further suggest that the relationship between accuracy and fluency is best evaluated at the segment (or sentence) level, and that the trade off between these dimensions has implications both for assessing translation quality and developing improved MT systems.

Andrew Gambardella, Yusuke Iwasawa, Yutaka Matsuo

The ability (and inability) of large language models (LLMs) to perform arithmetic tasks has been the subject of much theoretical and practical debate. We show that LLMs are frequently able to correctly and confidently predict the first digit of n-digit by m-digit multiplication tasks without using chain of thought reasoning, despite these tasks require compounding operations to solve. Simultaneously, LLMs in practice often fail to correctly or confidently predict the last digit of an n-digit by m-digit multiplication, a task equivalent to 1-digit by 1-digit multiplication which can be easily learned or memorized. We show that the latter task can be solved more robustly when the LLM is conditioned on all of the correct higher-order digits, which on average increases the confidence of the correct last digit on 5-digit by 5-digit multiplication tasks using Llama 2-13B by over 230% (0.13→0.43) and Mistral-7B by 150% (0.22→0.55).

Timothee Mickus, Stig-Arne Grönroos, Joseph Attieh

Whether embedding spaces use all their dimensions equally, i.e., whether they are isotropic, has been a recent subject of discussion. Evidence has been accrued both for and against enforcing isotropy in embedding spaces. In the present paper, we stress that isotropy imposes requirements on the embedding space that are not compatible with the presence of clusters—which also negatively impacts linear classification objectives. We demonstrate this fact both empirically and mathematically and use it to shed light on previous results from the literature.

Xinfeng Wang, Jin Cui, Yoshimi Suzuki, Fumiyo Fukumoto

Large language model (LLM)-based recommender models that bridge users and items through textual prompts for effective semantic reasoning have gained considerable attention. However, few methods consider the underlying rationales behind interactions, such as user preferences and item attributes, limiting the reasoning ability of LLMs for recommendations. This paper proposes a rationale distillation recommender (RDRec), a compact model designed to learn rationales generated by a larger language model (LM). By leveraging rationales from reviews related to users and items, RDRec remarkably specifies their profiles for recommendations. Experiments show that RDRec achieves state-of-the-art (SOTA) performance in both top-N and sequential recommendations. Our code is available online.

Hongyi Yuan, Keming Lu, Fei Huang, Zheng Yuan, Chang Zhou

Large language models (LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative decoding and contrastive decoding, we introduce Speculative Contrastive Decoding (SCD), a straightforward yet powerful decoding approach that leverages predictions from smaller language models (LMs) to achieve both decoding acceleration and quality improvement. Extensive evaluations and analyses on four diverse language tasks demonstrate the effectiveness of SCD, showing that decoding efficiency and quality can compatibly benefit from one smaller LM.

Saliha Muradoglu, Michael Ginn, Miikka Silfverberg, Mans Hulden

Active learning (AL) aims to lower the demand of annotation by selecting informative unannotated samples for the model building. In this paper, we explore the importance of conscious experimental design in the language documentation and description setting, particularly the distribution of the unannotated sample pool. We focus on the task of morphological inflection using a Transformer model. We propose context motivated benchmarks: a baseline and skyline. The baseline describes the frequency weighted distribution encountered in natural speech. We simulate this using Wikipedia texts. The skyline defines the more common approach, uniform sampling from a large, balanced corpus (UniMorph, in our case), which often yields mixed results. We note the unrealistic nature of this unannotated pool. When these factors are considered, our results show a clear benefit to targeted sampling.

Yewei Song, Cedric Lothritz, Daniel Tang, Tegawendé Bissyandé, Jacques Klein

This paper revisits recent code similarity evaluation metrics, particularly focusing on the application of Abstract Syntax Tree (AST) editing distance in diverse programming languages. In particular, we explore the usefulness of these metrics and compare them to traditional sequence similarity metrics. Our experiments showcase the effectiveness of AST editing distance in capturing intricate code structures, revealing a high correlation with established metrics. Furthermore, we explore the strengths and weaknesses of AST editing distance and prompt-based GPT similarity scores in comparison to BLEU score, execution match, and Jaccard Similarity. We propose, optimize, and publish an adaptable metric that demonstrates effectiveness across all tested languages, representing an enhanced version of Tree Similarity of Edit Distance (TSED).

Andrew Zhu, Alyssa Hwang, Liam Dugan, Chris Callison-Burch

One type of question that is commonly found in day-to-day scenarios is “fan-out” questions, complex multi-hop, multi-document reasoning questions that require finding information about a large number of entities. However, there exist few resources to evaluate this type of question-answering capability among large language models. To evaluate complex reasoning in LLMs more fully, we present FanOutQA, a high-quality dataset of fan-out question-answer pairs and human-annotated decompositions with English Wikipedia as the knowledge base. We formulate three benchmark settings across our dataset and benchmark 7 LLMs, including GPT-4, LLaMA 2, Claude-2.1, and Mixtral-8x7B, finding that contemporary models still have room to improve reasoning over inter-document dependencies in a long context. We provide our dataset, along with open-source tools to run models to encourage evaluation.

Ruoyao Wang, Graham Todd, Ziang Xiao, Xingdi Yuan, Marc-Alexandre Côté, Peter Clark, Peter Jansen

Virtual environments play a key role in benchmarking advances in complex planning and decision-making tasks but are expensive and complicated to build by hand. Can current language models themselves serve as world simulators, correctly predicting how actions change different world states, thus bypassing the need for extensive manual coding? Our goal is to answer this question in the context of text-based simulators. Our approach is to build and use a new benchmark, called ByteSized32-State-Prediction, containing a dataset of text game state transitions and accompanying game tasks. We use this to directly quantify, for the first time, how well LLMs can serve as text-based world simulators. We test GPT-4 on this dataset and find that, despite its impressive performance, it is still an unreliable world simulator without further innovations. This work thus contributes both new insights into current LLM’s capabilities and weaknesses, as well as a novel benchmark to track future progress as new models appear.

Chi Han, Jialiang Xu, Manling Li, Yi Fung, Chenkai Sun, Nan Jiang, Tarek Abdelzaher, Heng Ji

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain underexplored. In this work, we theoretically and empirically revisit output word embeddings and find that their linear transformations are equivalent to steering language model generation styles. We name such steers LM-Steers and find them existing in LMs of all sizes. It requires learning parameters equal to 0.2% of the original LMs’ size for steering each style. On tasks such as language model detoxification and sentiment control, LM-Steers can achieve comparable or superior performance compared with state-of-the-art controlled generation methods while maintaining a better balance with generation quality. The learned LM-Steer serves as a lens in text styles: it reveals that word embeddings are interpretable when associated with language model generations and can highlight text spans that most indicate the style differences. An LM-Steer is transferrable between different language models by an explicit form calculation. One can also continuously steer LMs simply by scaling the LM-Steer or compose multiple LM-Steers by adding their transformations. Our codes are publicly available at https://github.com/Glaciohound/LM-Steer.

Paul Roit, Aviv Slobodkin, Eran Hirsch, Arie Cattan, Ayal Klein, Valentina Pyatkin, Ido Dagan

Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument relations in a much wider context than just the sentence where the predicate was evoked. In this work, we reformulate the problem of argument detection through textual entailment to capture semantic relations across sentence boundaries. We propose a method that tests whether some semantic relation can be inferred from a full passage by first encoding it into a simple and standalone proposition and then testing for entailment against the passage. Our method does not require direct supervision, which is generally absent due to dataset scarcity, but instead builds on existing NLI and sentence-level SRL resources. Such a method can potentially explicate pragmatically understood relations into a set of explicit sentences. We demonstrate it on a recent document-level benchmark, outperforming some supervised methods and contemporary language models.

Tarek Naous, Michael J Ryan, Alan Ritter, Wei Xu

As the reach of large language models (LMs) expands globally, their ability to cater to diverse cultural contexts becomes crucial. Despite advancements in multilingual capabilities, models are not designed with appropriate cultural nuances. In this paper, we show that multilingual and Arabic monolingual LMs exhibit bias towards entities associated with Western culture. We introduce CAMeL, a novel resource of 628 naturally-occurring prompts and 20,368 entities spanning eight types that contrast Arab and Western cultures. CAMeL provides a foundation for measuring cultural biases in LMs through both extrinsic and intrinsic evaluations. Using CAMeL, we examine the cross-cultural performance in Arabic of 16 different LMs on tasks such as story generation, NER, and sentiment analysis, where we find concerning cases of stereotyping and cultural unfairness. We further test their text-infilling performance, revealing the incapability of appropriate adaptation to Arab cultural contexts. Finally, we analyze 6 Arabic pre-training corpora and find that commonly used sources such as Wikipedia may not be best suited to build culturally aware LMs, if used as they are without adjustment. We will make CAMeL publicly available at: https://github.com/tareknaous/camel

Yu Lu Liu, Su Lin Blodgett, Jackie Cheung, Q. Vera Liao, Alexandra Olteanu, Ziang Xiao

Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark’s measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices—e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks’ measurements.