论文检索

Nidhi Vakil, Hadi Amiri

Graph generation is the process of generating novel graphs with similar attributes to real world graphs. The explicit and precise control of granular structural attributes, such as node centrality and graph density, is crucial for effective graph generation. This paper introduces a controllable multi-objective translation model for text-attributed graphs, titled Controlled Graph Translator (CGT). It is designed to effectively and efficiently translate a given source graph to a target graph, while satisfying multiple desired graph attributes at granular level. Designed with an encoder-decoder architecture, CGT develops fusion and graph attribute predictor neural networks for controlled graph translation. We validate the effectiveness of CGT through extensive experiments on different genres of datasets. In addition, we illustrate the application of CGT in data augmentation and taxonomy creation, particularly in low resource settings.

Benedikt Boenninghoff, Henry Hosseini, Robert M. Nickel, Dorothea Kolossa

We are proposing a novel framework for author diarization, i.e. attributing comments in online discussions to individual authors. We consider an innovative approach that merges pre-trained neural representations of writing style with author-conditional encoder-decoder diarization, enhanced by a Conditional Random Field with Viterbi decoding for alignment refinement. Additionally, we introduce two new large-scale German language datasets, one for authorship verification and the other for author diarization. We evaluate the performance of our diarization framework on these datasets, offering insights into the strengths and limitations of this approach.

Yue Bai, Handong Zhao, Zhe Lin, Ajinkya Kale, Jiuxiang Gu, Tong Yu, Sungchul Kim, Yun Fu

CLIP revolutes vision-language pretraining by using contrastive learning on paired web data. However, the sheer size of these pretrained models makes full-model finetuning exceedingly costly. One common solution is the “adapter”, which finetunes a few additional parameters while freezing the backbone. It harnesses the heavy-duty backbone while offering a light finetuning for small downstream tasks. This synergy prompts us to explore the potential of augmenting large-scale backbones with traditional machine learning techniques. Often employed in traditional fields and overlooked in the large-scale era, these techniques could provide valuable enhancements. Herein, we delve into the “adapter ensembles” in the realm of large-scale pretrained vision-language models. We begin with a proof-of-concept study to establish the efficacy of combining multiple adapters. We then present extensive evidence showing these ensembles excel in a variety of settings, particularly when employing a Multi-Scale Attention (MSA) approach thoughtfully integrated into the ensemble framework. We further incorporate the LoRA to mitigate the additional parameter burden. We focus on vision-language retrieval, using different backbones under constraints of minimal data, parameters, and finetuning budgets. This research paves the way for a synergistic blend of traditional, yet effective, strategies with modern large-scale networks.

Arijit Nag, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti

Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs). A few of them have been trained on low-resource languages (LRLs) and give decent performance. Owing to the prohibitive costs of training LLMs, they are usually used as a network service, with the client charged by the count of input and output tokens. The number of tokens strongly depends on the script and language, as well as the LLM’s subword vocabulary. We show that LRLs are at a pricing disadvantage, because the well-known LLMs produce more tokens for LRLs than HRLs. This is because most currently popular LLMs are optimized for HRL vocabularies. Our objective is to level the playing field: reduce the cost of processing LRLs in contemporary LLMs while ensuring that predictive and generative qualities are not compromised. As means to reduce the number of tokens processed by the LLM, we consider code-mixing, translation, and transliteration of LRLs to HRLs. We perform an extensive study using the IndicXTREME classification and six generative tasks dataset, covering 15 Indic and 3 other languages, while using GPT-4 (one of the costliest LLM services released so far) as a commercial LLM. We observe and analyze interesting patterns involving token count, cost, and quality across a multitude of languages and tasks. We show that choosing the best policy to interact with the LLM can reduce cost by ~90% while giving better or comparable performance, compared to communicating with the LLM in the original LRL.

Ankan Mullick, Sombit Bose, Abhilash Nandy, Gajula Sai Chaitanya, Pawan Goyal

In task-oriented dialogue systems, intent detection is crucial for interpreting user queries and providing appropriate responses. Existing research primarily addresses simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents and extracting different intent spans. Additionally, there is a notable absence of multilingual, multi-intent datasets. This study addresses three critical tasks: extracting multiple intent spans from queries, detecting multiple intents, and developing a multilingual multi-label intent dataset. We introduce a novel multi-label multi-class intent detection dataset (MLMCID-dataset) curated from existing benchmark datasets. We also propose a pointer network-based architecture (MLMCID) to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets. Comprehensive analysis demonstrates the superiority of our pointer network based system over baseline approaches in terms of accuracy and F1-score across various datasets.

C. M. Downey, Terra Blevins, Dhwani Serai, Dwija Parikh, Shane Steinert-Threlkeld

Massively multilingual models are known to have limited utility in any one language, and to perform particularly poorly on low-resource languages. By contrast, targeted multinguality has been shown to benefit low-resource languages. To test this approach more rigorously, we systematically study best practices for adapting a pre-trained model to a language family. Focusing on the Uralic family as a test case, we adapt XLM-R under various configurations to model 15 languages; we then evaluate the performance of each experimental setting on two downstream tasks and 11 evaluation languages. Our adapted models significantly outperform mono- and multilingual baselines. A regression analysis reveals that adapted vocabulary size is relatively unimportant for low-resource languages, and that low-resource languages can be aggressively up-sampled during training at little detriment to performance in high-resource languages. These results introduce new best practices for performing language adaptation in a targeted setting.

Pritom Saha Akash, Kevin Chen-Chuan Chang

Topic modeling is a powerful technique for uncovering hidden themes within a collection of documents. However, the effectiveness of traditional topic models often relies on sufficient word co-occurrence, which is lacking in short texts. Therefore, existing approaches, whether probabilistic or neural, frequently struggle to extract meaningful patterns from such data, resulting in incoherent topics. To address this challenge, we propose a novel approach that leverages large language models (LLMs) to extend short texts into more detailed sequences before applying topic modeling. To further improve the efficiency and solve the problem of semantic inconsistency from LLM-generated texts, we propose to use prefix tuning to train a smaller language model coupled with a variational autoencoder for short-text topic modeling. Our method significantly improves short-text topic modeling performance, as demonstrated by extensive experiments on real-world datasets with extreme data sparsity, outperforming current state-of-the-art topic models.

Shabnam Behzad, Amir Zeldes, Nathan Schneider

In addition to asking questions about facts in the world, some internet users—in particular, second language learners—ask questions about language itself. Depending on their proficiency level and audience, they may pose these questions in an L1 (first language) or an L2 (second language). We investigate how multilingual LLMs perform at crosslingual metalinguistic question answering. Focusing on binary questions about sentence grammaticality constructed from error-annotated learner corpora, we prompt three LLMs (Aya, Llama, and GPT) in multiple languages, including English, German, Korean, Russian, and Ukrainian. Our study reveals that the language of the prompt can significantly affect model performance, and despite English being the dominant training language for all three models, prompting in a different language with questions about English often yields better results.

Jacob Morrison, Noah A. Smith, Hannaneh Hajishirzi, Pang Wei Koh, Jesse Dodge, Pradeep Dasigi

Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can cause the models to forget older skills. In this work, we investigate the effectiveness of adding new skills to preexisting models by training on the new skills in isolation and later merging with the general model (e.g. using task vectors). In experiments focusing on scientific literature understanding, safety, and coding, we find that the parallel-train-then-merge procedure, which is significantly cheaper than retraining the models on updated data mixtures, is often comparably effective. Our experiments also show that parallel training is especially well-suited for enabling safety features in LMs relative to continued finetuning and retraining, as it dramatically improves model compliance with safe prompts while preserving its ability to refuse dangerous or harmful prompts.

Melanie Walsh, Anna Preus, Maria Antoniak

Large language models (LLMs) can now generate and recognize poetry. But what do LLMs really know about poetry? We develop a task to evaluate how well LLMs recognize one aspect of English-language poetry—poetic form—which captures many different poetic features, including rhyme scheme, meter, and word or line repetition. By using a benchmark dataset of over 4.1k human expert-annotated poems, we show that state-of-the-art LLMs can successfully identify both common and uncommon fixed poetic forms—such as sonnets, sestinas, and pantoums—with surprisingly high accuracy. However, performance varies significantly by poetic form; the models struggle to identify unfixed poetic forms, especially those based on topic or visual features. We additionally measure how many poems from our benchmark dataset are present in popular pretraining datasets or memorized by GPT-4, finding that pretraining presence and memorization may improve performance on this task, but results are inconclusive. We release a benchmark evaluation dataset with 1.4k public domain poems and form annotations, results of memorization experiments and data audits, and code.

Shashank Sonkar, Naiming Liu, MyCo Le, Richard Baraniuk

This paper introduces MalAlgoQA, a novel dataset designed to evaluate the counterfactual reasoning capabilities of Large Language Models (LLMs) through a pedagogical approach. The dataset comprises mathematics and reading comprehension questions, each accompanied by four answer choices and their corresponding rationales. At the heart of MalAlgoQA are “malgorithms” - rationales behind incorrect answer choices that represent flawed yet logically coherent reasoning paths. These malgorithms serve as counterfactual scenarios, allowing us to assess an LLM’s ability to identify and analyze flawed reasoning patterns. We propose the Malgorithm Identification task, where LLMs are assessed based on their ability to identify corresponding malgorithm given an incorrect answer choice. To evaluate the model performance, we introduce two metrics: Algorithm Identification Accuracy (AIA) for correct answer rationale identification, and Malgorithm Identification Accuracy (MIA) for incorrect answer rationale identification. Our experiments reveal that state-of-the-art LLMs exhibit significant performance drops in MIA compared to AIA, highlighting the challenges in counterfactual reasoning.Surprisingly, we find that the chain-of-thought prompting technique not only fails to consistently enhance MIA but can sometimes lead to underperformance compared to simple prompting. These findings have important implications for developing LLMs with improved counterfactual reasoning, particularly relevant for AI-powered tutoring systems, where identifying and addressing student misconceptions is essential. MalAlgoQA dataset is available here.

Shashank Sonkar, Naiming Liu, Richard Baraniuk

The pursuit of personalized education has led to the integration of Large Language Models (LLMs) in developing intelligent tutoring systems. To better understand and adapt to individual student needs, including their misconceptions, LLMs need to be trained on extensive datasets of student-tutor dialogues. Our research uncovers a fundamental challenge in this approach: the “Student Data Paradox”. This paradox emerges when LLMs, trained on student data to understand learner behavior, inadvertently compromise their own factual knowledge and reasoning abilities. We investigate this paradox by training state-of-the-art language models on student-tutor dialogue datasets and evaluating their performance across multiple benchmarks. These benchmarks assess various aspects of language model capabilities, including reasoning, truthfulness, and common sense understanding. Our findings reveal significant declines in the models’ performance across these diverse benchmarks, indicating a broad impact on their capabilities when trained to model student behavior. Our research makes two primary contributions: (1) empirical demonstration of the Student Data Paradox through quantitative analysis of model performance, and (2) introduction of “hallucination tokens” as a mitigation strategy. These tokens, while improving performance, highlight the persistent challenge of balancing accurate student behavior modeling with maintaining the LLM’s integrity as an educational tool.This study emphasizes the need for innovative solutions to reconcile the conflicting goals of faithfully understanding diverse student cognition while preserving the model’s ability to provide accurate information and guidance.

Arnav Hiray, Yunsong Liu, Mingxiao Song, Agam Shah, Sudheer Chava

U.S. congressional hearings significantly influence the national economy and social fabric, impacting individual lives. Despite their importance, there is a lack of comprehensive datasets for analyzing these discourses. To address this, we propose the **Co**ngress **Co**mmittee **H**earing **D**ataset (CoCoHD), covering hearings from 1997 to 2024 across 86 committees, with 32,697 records. This dataset enables researchers to study policy language on critical issues like healthcare, LGBTQ+ rights, and climate justice. We demonstrate its potential with a case study on 1,000 energy-related sentences, analyzing the Energy and Commerce Committee’s stance on fossil fuel consumption. By fine-tuning pre-trained language models, we create energy-relevant measures for each hearing. Our market analysis shows that natural language analysis using CoCoHD can predict and highlight trends in the energy sector.

Xinshu Shen, Hongyi Wu, Yadong Zhang, Man Lan, Xiaopeng Bai, Shaoguang Mao, Yuanbin Wu, Xinlin Zhuang, Li Cai

Grammatical Error Correction (GEC) is a crucial technique in Automated Essay Scoring (AES) for evaluating the fluency of essays. However, in Chinese, existing GEC datasets often fail to consider the importance of specific grammatical error types within compositional scenarios, lack research on data collected from native Chinese speakers, and largely overlook cross-sentence grammatical errors. Furthermore, the measurement of the overall fluency of an essay is often overlooked. To address these issues, we present CEFA (Chinese Essay Fluency Assessment), an extensive corpus that is derived from essays authored by native Chinese-speaking primary and secondary students and encapsulates essay fluency scores along with both coarse and fine-grained grammatical error types and corrections. Experiments employing various benchmark models on CEFA substantiate the challenge of our dataset. Our findings further highlight the significance of fine-grained annotations in fluency assessment and the mutually beneficial relationship between error types and corrections

Muhammad Umair, Vasanth Sarathy, Jan Ruiter

Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken Dialogue Systems (SDS), such as their ability to respond at appropriate times. However, existing models often struggle to predict opportunities for speaking — called Transition Relevance Places (TRPs) — in natural, unscripted conversations, focusing only on turn-final TRPs and not within-turn TRPs. To address these limitations, we introduce a novel dataset of participant-labeled within-turn TRPs and use it to evaluate the performance of state-of-the-art LLMs in predicting opportunities for speaking. Our experiments reveal the current limitations of LLMs in modeling unscripted spoken interactions, highlighting areas for improvement and paving the way for more naturalistic dialogue systems.

Subramanian Chidambaram, Li Erran Li, Min Bai, Xiaopeng Li, Kaixiang Lin, Xiong Zhou, Alex C. Williams

Large Language Models (LLMs) are increasingly used for generating code solutions, empowered by features like self-debugging and self-reflection. However, LLMs often struggle with complex programming problems without human guidance. This paper investigates the strategies employed by expert programmers to steer code-generating LLMs toward successful outcomes. Through a study involving experts using natural language to guide GPT-4, Gemini Ultra, and, Claude 3.5 Sonnet on highly difficult programming challenges, we frame our analysis using the “Socratic Feedback” paradigm for understanding effective steering strategies. By analyzing 30 conversational transcripts across all three models, we map observed feedback strategies to five stages of Socratic Questioning: Definition, Elenhus, Maieutic, Dialectic, and Counter-factual reasoning. We find evidence that by employing a combination of different Socratic feedback strategies across multiple turns, programmers successfully guided the models to solve 74% of the problems that the models initially failed to solve on their own.

Joseph J Peper, Wenzhao Qiu, Ryan Bruggeman, Yi Han, Estefania Ciliotta Chehade, Lu Wang

We explore *implicit opinion extraction* as a new component of aspect-based sentiment analysis (ABSA) systems. Prior work in ABSA has investigated opinion extraction as an important subtask, however, these works only label concise, *explicitly*-stated opinion spans. In this work, we present **Shoes-ACOSI**, a new and challenging ABSA dataset in the e-commerce domain with implicit opinion span annotations, the first of its kind. Shoes-ACOSI builds upon the existing Aspect-Category-Opinion-Sentiment (ACOS) quadruple extraction task, extending the task to quintuple extraction—now localizing and differentiating both implicit and explicit opinion. In addition to the new annotation schema, our dataset contains paragraph-length inputs which, importantly, present complex challenges through increased input length, increased number of sentiment expressions, and more mixed-sentiment-polarity examples when compared with existing benchmarks. We quantify the difficulty of our new dataset by evaluating with state-of-the-art fully-supervised and prompted-LLM baselines. We find our dataset presents significant challenges for both supervised models and LLMs, particularly from the new implicit opinion extraction component of the ACOSI task, highlighting the need for continued research into implicit opinion understanding.

Isabel Cachola, Silviu Cucerzan, Allen Herring, Vuksan Mijovic, Erik Oveson, Sujay Kumar Jauhar

Authors seeking to communicate with broader audiences often share their ideas in various document formats, such as slide decks, newsletters, reports, and posters. Prior work on document generation has generally tackled the creation of each separate format to be a different task, leading to fragmented learning processes, redundancy in models and methods, and disjointed evaluation. We consider each of these documents as templatic views of the same underlying knowledge/content, and we aim to unify the generation and evaluation of these templatic views. We begin by showing that current LLMs are capable of generating various document formats with little to no supervision. Further, a simple augmentation involving a structured intermediate representation can improve performance, especially for smaller models. We then introduce a novel unified evaluation framework that can be adapted to measuring the quality of document generators for heterogeneous downstream applications. This evaluation is adaptable to a range of user defined criteria and application scenarios, obviating the need for task specific evaluation metrics. Finally, we conduct a human evaluation, which shows that people prefer 82% of the documents generated with our method, while correlating more highly with our unified evaluation framework than prior metrics in the literature.

Sonny George, Chris Sypherd, Dylan Cashman

Large language model (LLM) agents show promise in an increasing number of domains. In many proposed applications, it is expected that the agent reasons over accumulated experience presented in an input prompt. We propose the OEDD (Operationalize Experience Despite Distraction) corpus, a human-annotator-validated body of scenarios with pre-scripted agent histories where the agent must make a decision based on disparate experiential information in the presence of a distractor. We evaluate three state-of-the-art LLMs (GPT-3.5 Turbo, GPT-4o, and Gemini 1.5 Pro) using a minimal chain-of-thought prompting strategy and observe that when (1) the input context contains over 1,615 tokens of historical interactions, (2) a crucially decision-informing premise is the rightful conclusion over two disparate environment premises, and (3) a trivial, but distracting red herring fact follows, all LLMs perform worse than random choice at selecting the better of two actions. Our code and test corpus are publicly available at: [github.com/sonnygeorge/OEDD](github.com/sonnygeorge/OEDD).

Chuhan Li, Ziyao Shangguan, Yilun Zhao, Deyuan Li, Yixin Liu, Arman Cohan

Existing evaluation benchmarks for foundation models in understanding scientific literature predominantly focus on single-document, text-only tasks. Such benchmarks often do not adequately represent the complexity of research workflows, which typically also involve interpreting non-textual data, such as figures and tables, and gathering information across multiple documents and related literature. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3Sci QA consists of 1452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster represents a primary paper along with all its cited documents, mirroring the workflow of comprehending a single paper by requiring multi-modal and multi-document data. With M3SciQA, we conduct a comprehensive evaluation of 18 frontier foundation models. Our results indicate that current foundation models still significantly underperform compared to human experts in multi-modal information retrieval and in reasoning across multiple scientific documents. Additionally, we explore the implications of these findings for the future advancement of applying foundation models in multi-modal scientific literature analysis.