论文检索

Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong, Wei Bi

Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathematical knowledge or merely rely on shortcuts for mathematical reasoning. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs’ math reasoning capability by testing a wide range of question variations. We introduce the adversarial grade school math (GSM-Plus) dataset, an extension of GSM8K augmented with various mathematical perturbations. Our experiments on 25 LLMs and 4 prompting techniques show that while LLMs exhibit different levels of math reasoning abilities, their performances are far from robust. In particular, even for problems that have been solved in GSM8K, LLMs can make mistakes when new statements are added or the question targets are altered. We also explore whether more robust performance can be achieved by composing existing prompting methods, in which we try an iterative method that generates and verifies each intermediate thought based on its reasoning goal and calculation result.

Chengyu Huang, Zeqiu Wu, Yushi Hu, Wenya Wang

While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to these issues would be to include in-text citations referring to external documents as evidence. While previous works have directly prompted LLMs to generate in-text citations, their performances are far from satisfactory, especially when it comes to smaller LLMs. In this work, we propose an effective training framework using fine-grained rewards to teach LLMs to generate highly supportive and relevant citations, while ensuring the correctness of their responses. We also conduct a systematic analysis of applying these fine-grained rewards to common LLM training strategies, demonstrating its advantage over conventional practices. We conduct extensive experiments on Question Answering (QA) datasets taken from the ALCE benchmark and validate the model’s generalizability using EXPERTQA. On LLaMA-2-7B, the incorporation of fine-grained rewards achieves the best performance among the baselines, even surpassing that of GPT-3.5-turbo.

Xiao Wei, Qi Xu, Hang Yu, Qian Liu, Erik Cambria

The current charge prediction datasets mostly focus on single-defendant criminal cases.However, real-world criminal cases usually involve multiple defendants whose criminal facts are intertwined. In an early attempt to fill this gap, we introduce a new benchmark that encompasses legal cases involving multiple defendants, where each defendant is labeled with a charge and four types of crime elements, i.e., Object Element, Objective Element, Subject Element, and Subjective Element. Based on the dataset, we further develop an interpretable model called EJudge that incorporates crime elements and legal rules to infer charges. We observe that predicting crime charges while providing corresponding rationales benefits the interpretable AI system. Extensive experiments show that EJudge significantly surpasses state-of-the-art methods, which verify the importance of crime elements and legal rules in multi-defendant charge prediction. The source code and dataset are available at https://anonymous.4open.science/r/MCP_1-6010.

Zefan Cai, Po-Nien Kung, Ashima Suvarna, Mingyu Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang, Nanyun Peng

Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types, and prompt them with unseen event definitions. These approaches yield sporadic successes, yet generally fall short of expectations.In this work, we aim to improve zero-shot event detection by training models to better follow event definitions. We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while existing event extraction datasets focus on annotating many high-quality examples for a few event types. To verify our hypothesis, we construct an automatically generated Diverse Event Definition (DivED) dataset and conduct comparative studies. Our experiments reveal that a large number of event types (200) and diverse event definitions can significantly boost event extraction performance; on the other hand, the performance does not scale with over ten examples per event type.Beyond scaling, we incorporate event ontology information and hard-negative samples during training, further boosting the performance. Based on these findings, we fine-tuned a LLaMA-2-7B model on our DivED dataset, yielding performance that surpasses SOTA large language models like GPT-3.5 across three open benchmarks on zero-shot event detection.

Mathieu Ravaut, Aixin Sun, Nancy Chen, Shafiq Joty

Large language models (LLMs) excel in abstractive summarization tasks, delivering fluent and pertinent summaries. Recent advancements have extended their capabilities to handle long-input contexts, exceeding 100k tokens. However, in question answering, language models exhibit uneven utilization of their input context. They tend to favor the initial and final segments, resulting in a U-shaped performance pattern concerning where the answer is located within the input. This bias raises concerns, particularly in summarization where crucial content may be dispersed throughout the source document(s). Besides, in summarization, mapping facts from the source to the summary is not trivial as salient content is usually re-phrased. In this paper, we conduct the first comprehensive study on context utilization and position bias in summarization. Our analysis encompasses 6 LLMs, 10 datasets, and 5 evaluation metrics. We introduce a new evaluation benchmark called MiddleSum on the which we benchmark two alternative inference methods to alleviate position bias: hierarchical summarization and incremental summarization. Our code and data can be found here: https://github.com/ntunlp/MiddleSum.

Yanyang Li, Shuo Liang, Michael Lyu, Liwei Wang

Recent advancements in long-context modeling have enhanced language models (LMs) for complex tasks across multiple NLP applications. Despite this progress, we find that these models struggle with multi-hop reasoning and exhibit decreased performance in the presence of noisy contexts. In this paper, we introduce Reasoning with Attributions, a novel approach that prompts LMs to supply attributions for each assertion during their reasoning. We validate our approach through experiments on three multi-hop datasets, employing both proprietary and open-source models, and demonstrate its efficacy and resilience. Furthermore, we explore methods to augment reasoning capabilities via fine-tuning and offer an attribution-annotated dataset and a specialized training strategy. Our fine-tuned model achieves competitive performance on multi-hop reasoning benchmarks, closely paralleling proprietary LMs such as ChatGPT and Claude-instant.

Guizhen Chen, Liying Cheng, Anh Tuan Luu, Lidong Bing

Computational argumentation has become an essential tool in various domains, including law, public policy, and artificial intelligence. It is an emerging research field in natural language processing that attracts increasing attention. Research on computational argumentation mainly involves two types of tasks: argument mining and argument generation. As large language models (LLMs) have demonstrated impressive capabilities in understanding context and generating natural language, it is worthwhile to evaluate the performance of LLMs on diverse computational argumentation tasks. This work aims to embark on an assessment of LLMs, such as ChatGPT, Flan models, and LLaMA2 models, in both zero-shot and few-shot settings. We organize existing tasks into six main categories and standardize the format of fourteen openly available datasets. In addition, we present a new benchmark dataset on counter speech generation that aims to holistically evaluate the end-to-end performance of LLMs on argument mining and argument generation. Extensive experiments show that LLMs exhibit commendable performance across most of the datasets, demonstrating their capabilities in the field of argumentation. Our analysis offers valuable suggestions for evaluating computational argumentation and its integration with LLMs in future research endeavors.

Leon Weber-Genzel, Siyao Peng, Marie-Catherine De Marneffe, Barbara Plank

Human label variation arises when annotators assign different labels to the same item for valid reasons, while annotation errors occur when labels are assigned for invalid reasons. These two issues are prevalent in NLP benchmarks, yet existing research has studied them in isolation. To the best of our knowledge, there exists no prior work that focuses on teasing apart error from signal, especially in cases where signal is beyond black-and-white.To fill this gap, we introduce a systematic methodology and a new dataset, VariErr (variation versus error), focusing on the NLI task in English. We propose a 2-round annotation procedure with annotators explaining each label and subsequently judging the validity of label-explanation pairs.VariErr contains 7,732 validity judgments on 1,933 explanations for 500 re-annotated MNLI items. We assess the effectiveness of various automatic error detection (AED) methods and GPTs in uncovering errors versus human label variation. We find that state-of-the-art AED methods significantly underperform GPTs and humans. While GPT-4 is the best system, it still falls short of human performance. Our methodology is applicable beyond NLI, offering fertile ground for future research on error versus plausible variation, which in turn can yield better and more trustworthy NLP systems.

Mohammad Javad Hosseini, Andrey Petrov, Alex Fabrikant, Annie Louis

Natural Language Inference (NLI) remains an important benchmark task for LLMs. NLI datasets are a springboard for transfer learning to other semantic tasks, and NLI models are standard tools for identifying the faithfulness of model-generated text. There are several large scale NLI datasets today, and models have improved greatly by hill-climbing on these collections. Yet their realistic performance on out-of-distribution/domain data is less well-understood. We explore the opportunity for synthetic high-quality datasets to adapt NLI models for zero-shot use in downstream applications across new and unseen text domains. We demonstrate a new approach for generating NLI data in diverse domains and lengths, so far not covered by existing training sets. The resulting examples have meaningful premises, the hypotheses are formed in creative ways rather than simple edits to a few premise tokens, and the labels have high accuracy. We show that models trained on this data (685K synthetic examples) have the best generalization to completely new downstream test settings. On the TRUE benchmark, a T5-small model trained with our data improves around 7% on average compared to training on the best alternative dataset. The improvements are more pronounced for smaller models, while still meaningful on a T5 XXL model. We also demonstrate gains on test sets when in-domain training data is augmented with our domain-general synthetic data.

Qian Yang, Jin Xu, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Zhou Zhao, Chang Zhou 等

Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as automatic speech recognition, and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement.In this paper, we introduce AIR-Bench (Audio InstRuction Benchmark), the first benchmark designed to evaluate the ability of LALMs to understand various types of audio signals (including human speech, natural sounds, and music), and furthermore, to interact with humans in the textual format. AIR-Bench encompasses two dimensions: foundation and chat benchmarks. The former consists of 19 tasks with approximately 19k single-choice questions, intending to inspect the basic single-task ability of LALMs. The latter one contains 2k instances of open-ended question-and-answer data, directly assessing the comprehension of the model on complex audio and its capacity to follow instructions. Both benchmarks require the model to generate hypotheses directly. We design a unified framework that leverages advanced language models, such as GPT-4, to evaluate the scores of generated hypotheses given the meta-information of the audio. Experimental results demonstrate a high level of consistency between GPT-4-based evaluation and human evaluation. By revealing the limitations of existing LALMs through evaluation results, AIR-Bench can provide insights into the direction of future research. Dataset and evaluation code are available at https://github.com/OFA-Sys/AIR-Bench.

Xianming Li, Jing Li

Text embedding is pivotal in semantic textual similarity (STS) tasks, which are crucial components in Large Language Model (LLM) applications. STS learning largely relies on the cosine function as the optimization objective to reflect semantic similarity. However, the cosine has saturation zones rendering vanishing gradients and hindering learning subtle semantic differences in text embeddings. To address this issue, we propose a novel Angle-optimized Embedding model, AoE. It optimizes angle differences in complex space to explore similarity in saturation zones better. To set up a comprehensive evaluation, we experimented with existing short-text STS, our newly collected long-text STS, and downstream task datasets. Extensive experimental results on STS and MTEB benchmarks show that AoE significantly outperforms popular text embedding models neglecting cosine saturation zones. It highlights that AoE can produce high-quality text embeddings and broadly benefit downstream tasks.

Bi-Cheng Yan, Jiun-Ting Li, Yi-Cheng Wang, Hsin Wei Wang, Tien-Hong Lo, Yung-Chang Hsu, Wei-Cheng Chao, Berlin Chen

Automatic pronunciation assessment (APA) manages to quantify a second language (L2) learner’s pronunciation proficiency in a target language by providing fine-grained feedback with multiple pronunciation aspect scores at various linguistic levels. Most existing efforts on APA typically parallelize the modeling process, namely predicting multiple aspect scores across various linguistic levels simultaneously. This inevitably makes both the hierarchy of linguistic units and the relatedness among the pronunciation aspects sidelined. Recognizing such a limitation, we in this paper first introduce HierTFR, a hierarchal APA method that jointly models the intrinsic structures of an utterance while considering the relatedness among the pronunciation aspects. We also propose a correlation-aware regularizer to strengthen the connection between the estimated scores and the human annotations. Furthermore, novel pre-training strategies tailored for different linguistic levels are put forward so as to facilitate better model initialization. An extensive set of empirical experiments conducted on the speechocean762 benchmark dataset suggest the feasibility and effectiveness of our approach in relation to several competitive baselines.

Zhenhua Liu, Tong Zhu, Chuanyuan Tan, Bing Liu, Haonan Lu, Wenliang Chen

Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model’s internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy.

Weitao Li, Junkai Li, Weizhi Ma, Yang Liu

Large language models (LLMs) exhibit powerful general intelligence across diverse scenarios, including their integration into chatbots. However, a vital challenge of LLM-based chatbots is that they may produce hallucinated content in responses, which significantly limits their applicability. Various efforts have been made to alleviate hallucination, such as retrieval augmented generation and reinforcement learning with human feedback, but most of them require additional training and data annotation. In this paper, we propose a novel post-hoc Citation-Enhanced Generation (CEG) approach combined with retrieval argumentation. Unlike previous studies that focus on preventing hallucinations during generation, our method addresses this issue in a post-hoc way. It incorporates a retrieval module to search for supporting documents relevant to the generated content, and employs a natural language inference-based citation generation module. Once the statements in the generated content lack of reference, our model can regenerate responses until all statements are supported by citations. Note that our method is a training-free plug-and-play plugin that is capable of various LLMs. Experiments on various hallucination-related datasets show our framework outperforms state-of-the-art methods in both hallucination detection and response regeneration on three benchmarks. Our code and datasets can be found at https://github.com/Tsinghua-dhy/CEG.

Zhaorui Yang, Tianyu Pang, Haozhe Feng, Han Wang, Wei Chen, Minfeng Zhu, Qian Liu

The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities. In this paper, we posit that the distribution gap between task datasets and the LLMs serves as the primary underlying cause. To address the problem, we introduce Self-Distillation Fine-Tuning (SDFT), a novel approach that bridges the distribution gap by guiding fine-tuning with a distilled dataset generated by the model itself to match its original distribution. Experimental results on the Llama-2-chat model across various benchmarks demonstrate that SDFT effectively mitigates catastrophic forgetting while achieving comparable or superior performance on downstream tasks compared to the vanilla fine-tuning. Moreover, SDFT demonstrates the potential to maintain the helpfulness and safety alignment of LLMs. Our code is available at https://github.com/sail-sg/sdft.

Runlong Zhou, Simon Du, Beibin Li

As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning (SFT) on a limited offline dataset does not yield good performance. However, only a few works attempted to directly train the LMs within interactive decision-making environments. We aim to create an effective approach to fine-tune LMs with online reinforcement learning (RL) in these environments. We propose Reflect-RL, a two-player system to fine-tune an LM using SFT and online RL, where a frozen reflection model (player) assists the policy model (player). To generate data for the warm-up SFT stage, we use negative example generation to enhance the error-correction ability of the reflection model. Furthermore, we designed single-prompt action enumeration and applied curriculum learning to allow the policy model to learn more efficiently. Empirically, we verify that Reflect-RL outperforms SFT and online RL without reflection. Testing results indicate GPT-2 XL 1.56B fine-tuned with Reflect-RL outperforms larger open-source LMs, such as Mistral 7B. The benchmarks, dataset, and code involved in this work are publicly available: https://github.com/zhourunlong/Reflect-RL.

Masato Mita, Soichiro Murakami, Akihiko Kato, Peinan Zhang

In response to the limitations of manual ad creation, significant research has been conducted in the field of automatic ad text generation (ATG). However, the lack of comprehensive benchmarks and well-defined problem sets has made comparing different methods challenging. To tackle these challenges, we standardize the task of ATG and propose a first benchmark dataset, CAMERA, carefully designed and enabling the utilization of multi-modal information and facilitating industry-wise evaluations. Our extensive experiments with a variety of nine baselines, from classical methods to state-of-the-art models including large language models (LLMs), show the current state and the remaining challenges. We also explore how existing metrics in ATG and an LLM-based evaluator align with human evaluations.

Daechul Ahn, Yura Choi, Youngjae Yu, Dongyeop Kang, Jonghyun Choi

Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs). Previous approaches for VLMMs involve Supervised Fine-Tuning (SFT) with instruction-tuned datasets, integrating LLM with visual encoders, and additional learnable parameters. Here, aligning video with text, and vice versa, remains a challenge, primarily due to the insufficient quality and quantity of multimodal instruction-tune data compared to that of text-only. This discrepancy often results in alignments that poorly ground the video content. To address this, we present a novel alignment strategy that employs a multimodal AI system equipped with Reinforcement Learning from AI Feedback (RLAIF), providing self-preference feedback to refine itself and facilitating the alignment of video and text modalities. Our approach uniquely integrates detailed video descriptions as context into a multimodal AI system during the preference feedback generation to enrich the understanding of video content, a process we call context-aware reward modeling. Empirical evaluations on various video benchmarks demonstrate that our VLM-RLAIF outperforms existing approaches, including the SFT model. We commit to open-sourcing our code, models, and datasets to foster further research in this area.

Lucas Bandarkar, Davis Liang, Benjamin Muller, Mikel Artetxe, Satya Narayan Shukla, Donald Husa, Naman Goyal, Abhinandan Krishnan, Luke Zettlemoyer, Madian Khabsa

We present Belebele, a multiple-choice machine reading comprehension (MRC) dataset spanning 122 language variants. Significantly expanding the language coverage of natural language understanding (NLU) benchmarks, this dataset enables the evaluation of text models in high-, medium-, and low-resource languages. Each question is based on a short passage from the FLORES-200 dataset and has four multiple-choice answers. The questions were carefully curated to discriminate between models with different levels of general language comprehension. The English dataset on its own proves difficult enough to challenge state-of-the-art language models. Being fully parallel, this dataset enables direct comparison of model performance across all languages. We use this dataset to evaluate the capabilities of multilingual masked language models (MLMs) and large language models (LLMs). We present extensive results and findings, notably that despite significant cross-lingual transfer in English-centric LLMs, much smaller MLMs pretrained on balanced multilingual data still understand far more languages. Overall, Belebele opens up new avenues for evaluating and analyzing the multilingual capabilities of NLP systems.

Chufan Gao, Xuan Wang, Jimeng Sun

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