Steven Y. Feng

Sedrick Scott Keh, Steven Y. Feng, Varun Gangal et al. · cmu

Tongue twisters are meaningful sentences that are difficult to pronounce. The process of automatically generating tongue twisters is challenging since the generated utterance must satisfy two conditions at once: phonetic difficulty and semantic meaning. Furthermore, phonetic difficulty is itself hard to characterize and is expressed in natural tongue twisters through a heterogeneous mix of phenomena such as alliteration and homophony. In this paper, we propose PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically. We leverage phoneme representations to capture the notion of phonetic difficulty, and we train language models to generate original tongue twisters on two proposed task settings. To do this, we curate a dataset called PANCETTA, consisting of existing English tongue twisters. Through automatic and human evaluation, as well as qualitative analysis, we show that PANCETTA generates novel, phonetically difficult, fluent, and semantically meaningful tongue twisters.

Sedrick Scott Keh, Kevin Lu, Varun Gangal et al. · amazon-science, cmu

A personification is a figure of speech that endows inanimate entities with properties and actions typically seen as requiring animacy. In this paper, we explore the task of personification generation. To this end, we propose PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation. We curate a corpus of personifications called PersonifCorp, together with automatically generated de-personified literalizations of these personifications. We demonstrate the usefulness of this parallel corpus by training a seq2seq model to personify a given literal input. Both automatic and human evaluations show that fine-tuning with PersonifCorp leads to significant gains in personification-related qualities such as animacy and interestingness. A detailed qualitative analysis also highlights key strengths and imperfections of PINEAPPLE over baselines, demonstrating a strong ability to generate diverse and creative personifications that enhance the overall appeal of a sentence.

Steven Y. Feng, Vivek Khetan, Bogdan Sacaleanu et al.

We motivate and introduce CHARD: Clinical Health-Aware Reasoning across Dimensions, to investigate the capability of text generation models to act as implicit clinical knowledge bases and generate free-flow textual explanations about various health-related conditions across several dimensions. We collect and present an associated dataset, CHARDat, consisting of explanations about 52 health conditions across three clinical dimensions. We conduct extensive experiments using BART and T5 along with data augmentation, and perform automatic, human, and qualitative analyses. We show that while our models can perform decently, CHARD is very challenging with strong potential for further exploration.

Emmy Liu, Varun Gangal, Chelsea Zou et al. · cmu

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we outline plans for a family of benchmarks using synthetic, fully specified reference world models to stress-test and improve world modeling components.

Steven Y. Feng, Noah D. Goodman, Michael C. Frank

While high-performing language models are typically trained on hundreds of billions of words, human children become fluent language users with a much smaller amount of data. What are the features of the data they receive, and how do these features support language modeling objectives? To investigate this question, we train GPT-2 and RoBERTa models on 29M words of English child-directed speech and a new matched, synthetic dataset (TinyDialogues), comparing to OpenSubtitles, Wikipedia, and a heterogeneous blend of datasets from the BabyLM challenge. We evaluate the syntactic and semantic knowledge of these models using developmentally-inspired evaluations. Through pretraining experiments, we test whether the global developmental ordering or the local discourse ordering of children's training data supports high performance relative to other datasets. The local properties of the data affect model results, but surprisingly, global properties do not. Further, child language input is not uniquely valuable for training language models. These findings support the hypothesis that, rather than proceeding from better data, the child's learning algorithm is substantially more data-efficient than current language modeling techniques.

Emmy Liu, Varun Gangal, Michael Yu et al.

Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization, question answering, retrieval-augmented generation, and agentic interaction. This fragmentation makes it unclear whether a mitigation that works in one setting reduces hallucinations across contexts. Current benchmarks either require human annotation and fixed references that may be memorized, or rely on observations in settings that are difficult to reproduce. To study root causes, we introduce HalluWorld, an extensible benchmark grounded in an explicit reference-world formulation: a model hallucinates when it produces an observable claim that is false with respect to this world. Building on this view, we construct synthetic and semi-synthetic environments in which the reference world is fully specified, the model's view is controlled, and hallucination labels are generated automatically. HalluWorld spans gridworlds, chess, and realistic terminal tasks, enabling controlled variation of world complexity, observability, temporal change, and source-conflict policy, and disentangling hallucinations into fine-grained error categories. We evaluate frontier and open-weight language models across these settings and find consistent patterns: perceptual hallucination on directly observed information is near-solved for frontier models, while multi-step state tracking and causal forward simulation remain difficult and are not generally solved by extended thinking. In the terminal setting, models also struggle with when to abstain. The uneven profile of failures across probe types and domains suggests that hallucinations arise from distinct failure modes rather than a single capability. Our results suggest that controlled reference worlds offer a scalable and reproducible path toward measuring and reducing hallucinations in modern language models.

Karan Singh, Michael Yu, Varun Gangal et al.

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. However, the relationship between parametric knowledge acquired during pretraining and non-parametric knowledge accessed via retrieval remains poorly understood, especially under fixed data budgets. In this work, we systematically study the trade-off between pretraining corpus size and retrieval store size across a wide range of model and data scales. We train OLMo-2-based LMs ranging from 30M to 3B parameters on up to 100B tokens of DCLM data, while varying both pretraining data scale (1-150x the number of parameters) and retrieval store size (1-20x), and evaluate performance across a diverse suite of benchmarks spanning reasoning, scientific QA, and open-domain QA. We find that retrieval consistently improves performance over parametric-only baselines across model scales and introduce a three-dimensional scaling framework that models performance as a function of model size, pretraining tokens, and retrieval corpus size. This scaling manifold enables us to estimate optimal allocations of a fixed data budget between pretraining and retrieval, revealing that the marginal utility of retrieval depends strongly on model scale, task type, and the degree of pretraining saturation. Our results provide a quantitative foundation for understanding when and how retrieval should complement pretraining, offering practical guidance for allocating data resources in the design of scalable language modeling systems.

Long Phan, Alice Gatti, Ziwen Han et al. · amazon-science, apple-ml

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Steven Y. Feng, Varun Gangal, Jason Wei et al.

Data augmentation has recently seen increased interest in NLP due to more work in low-resource domains, new tasks, and the popularity of large-scale neural networks that require large amounts of training data. Despite this recent upsurge, this area is still relatively underexplored, perhaps due to the challenges posed by the discrete nature of language data. In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner. We first introduce and motivate data augmentation for NLP, and then discuss major methodologically representative approaches. Next, we highlight techniques that are used for popular NLP applications and tasks. We conclude by outlining current challenges and directions for future research. Overall, our paper aims to clarify the landscape of existing literature in data augmentation for NLP and motivate additional work in this area. We also present a GitHub repository with a paper list that will be continuously updated at https://github.com/styfeng/DataAug4NLP

Linda Zeng, Steven Y. Feng, Michael C. Frank

Multilingualism is incredibly common around the world, leading to many important theoretical and practical questions about how children learn multiple languages at once. For example, does multilingual acquisition lead to delays in learning? Are there better and worse ways to structure multilingual input? Many correlational studies address these questions, but it is surprisingly difficult to get definitive answers because children cannot be randomly assigned to be multilingual and data are typically not matched between languages. We use language model training as a method for simulating a variety of highly controlled exposure conditions, and create matched 100M-word mono- and bilingual datasets using synthetic data and machine translation. We train GPT-2 models on monolingual and bilingual data organized to reflect a range of exposure regimes, and evaluate their performance on perplexity, grammaticality, and semantic knowledge. Across model scales and measures, bilingual models perform similarly to monolingual models in one language, but show strong performance in the second language as well. These results suggest that there are no strong differences between different bilingual exposure regimes, and that bilingual input poses no in-principle challenges for agnostic statistical learners.

Steven Y. Feng, Alvin W. M. Tan, Michael C. Frank

Modern language models (LMs) must be trained on many orders of magnitude more words of training data than human children receive before they begin to produce useful behavior. Assessing the nature and origins of this "data gap" requires benchmarking LMs on human-scale datasets to understand how linguistic knowledge emerges from children's natural training data. Using transcripts from the BabyView dataset (videos from children ages 6-36 months), we investigate (1) scaling performance at child-scale data regimes, (2) variability in model performance across datasets from different children's experiences and linguistic predictors of dataset quality, and (3) relationships between model and child language learning outcomes. LMs trained on child data show acceptable scaling for grammar tasks, but lower scaling on semantic and world knowledge tasks than models trained on synthetic data; we also observe substantial variability on data from different children. Beyond dataset size, performance is most associated with a combination of distributional and interactional linguistic features, broadly consistent with what makes high-quality input for child language development. Finally, model likelihoods for individual words correlate with children's learning of those words, suggesting that properties of child-directed input may influence both model learning and human language development. Overall, understanding what properties make language data efficient for learning can enable more powerful small-scale language models while also shedding light on human language acquisition.

Bria Long, Robert Z. Sparks, Violet Xiang et al.

Human children far exceed modern machine learning algorithms in their sample efficiency, achieving high performance in key domains with much less data than current models. This ''data gap'' is a key challenge both for building intelligent artificial systems and for understanding human development. Egocentric video capturing children's experience--their ''training data''--is a key ingredient for comparison of humans and models and for the development of algorithmic innovations to bridge this gap. Yet there are few such datasets available, and extant data are low-resolution, have limited metadata, and importantly, represent only a small set of children's experiences. Here, we provide the first release of a large developmental egocentric video dataset--the BabyView dataset--recorded using a high-resolution camera with a large vertical field-of-view and gyroscope/accelerometer data. This 868 hour dataset includes egocentric videos from children spanning 6 months to 3 years of age in longitudinal, at-home contexts. We provide gold-standard annotations for the evaluation of speech transcription, speaker diarization, and human pose estimation, and evaluate models in each of these domains. We train self-supervised language and vision models and evaluate their transfer to out-of-distribution tasks, including syntactic structure learning, object recognition, depth estimation, and image segmentation. Although performance in each domain scales with dataset size, overall performance is relatively lower than when models are trained on curated datasets, especially in the visual domain. Our dataset stands as an open challenge for robust, human-like AI systems: how can such systems achieve human-levels of success on the same scale and distribution of training data as humans?

Steven Y. Feng, Kevin Lu, Zhuofu Tao et al.

We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation. We perform experiments using BART and T5 on concept-to-text generation, specifically the task of generative commonsense reasoning, or CommonGen. We call our approach VisCTG: Visually Grounded Concept-to-Text Generation. VisCTG involves captioning images representing appropriate everyday scenarios, and using these captions to enrich and steer the generation process. Comprehensive evaluation and analysis demonstrate that VisCTG noticeably improves model performance while successfully addressing several issues of the baseline generations, including poor commonsense, fluency, and specificity.

Steven Y. Feng, Jessica Huynh, Chaitanya Narisetty et al.

We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on generative commonsense reasoning, a.k.a. the CommonGen task, through experiments using both BART and T5 models. Through extensive automatic and human evaluation, we show that SAPPHIRE noticeably improves model performance. An in-depth qualitative analysis illustrates that SAPPHIRE effectively addresses many issues of the baseline model generations, including lack of commonsense, insufficient specificity, and poor fluency.

Varun Gangal, Steven Y. Feng, Malihe Alikhani et al.

Many implicit inferences exist in text depending on how it is structured that can critically impact the text's interpretation and meaning. One such structural aspect present in text with chronology is the order of its presentation. For narratives or stories, this is known as the narrative order. Reordering a narrative can impact the temporal, causal, event-based, and other inferences readers draw from it, which in turn can have strong effects both on its interpretation and interestingness. In this paper, we propose and investigate the task of Narrative Reordering (NAREOR) which involves rewriting a given story in a different narrative order while preserving its plot. We present a dataset, NAREORC, with human rewritings of stories within ROCStories in non-linear orders, and conduct a detailed analysis of it. Further, we propose novel task-specific training methods with suitable evaluation metrics. We perform experiments on NAREORC using state-of-the-art models such as BART and T5 and conduct extensive automatic and human evaluations. We demonstrate that although our models can perform decently, NAREOR is a challenging task with potential for further exploration. We also investigate two applications of NAREOR: generation of more interesting variations of stories and serving as adversarial sets for temporal/event-related tasks, besides discussing other prospective ones, such as for pedagogical setups related to language skills like essay writing and applications to medicine involving clinical narratives.

Steven Y. Feng, Varun Gangal, Dongyeop Kang et al.

In this paper, we investigate data augmentation for text generation, which we call GenAug. Text generation and language modeling are important tasks within natural language processing, and are especially challenging for low-data regimes. We propose and evaluate various augmentation methods, including some that incorporate external knowledge, for finetuning GPT-2 on a subset of Yelp Reviews. We also examine the relationship between the amount of augmentation and the quality of the generated text. We utilize several metrics that evaluate important aspects of the generated text including its diversity and fluency. Our experiments demonstrate that insertion of character-level synthetic noise and keyword replacement with hypernyms are effective augmentation methods, and that the quality of generations improves to a peak at approximately three times the amount of original data.

Aaron W. Li, Veronica Jiang, Steven Y. Feng et al.

For conversational AI and virtual assistants to communicate with humans in a realistic way, they must exhibit human characteristics such as expression of emotion and personality. Current attempts toward constructing human-like dialogue agents have presented significant difficulties. We propose Human Level Attributes (HLAs) based on tropes as the basis of a method for learning dialogue agents that can imitate the personalities of fictional characters. Tropes are characteristics of fictional personalities that are observed recurrently and determined by viewers' impressions. By combining detailed HLA data with dialogue data for specific characters, we present a dataset, HLA-Chat, that models character profiles and gives dialogue agents the ability to learn characters' language styles through their HLAs. We then introduce a three-component system, ALOHA (which stands for Artificial Learning of Human Attributes), that combines character space mapping, character community detection, and language style retrieval to build a character (or personality) specific language model. Our preliminary experiments demonstrate that two variations of ALOHA, combined with our proposed dataset, can outperform baseline models at identifying the correct dialogue responses of chosen target characters, and are stable regardless of the character's identity, the genre of the show, and the context of the dialogue.

Steven Y. Feng, Aaron W. Li, Jesse Hoey

In this paper, we present a novel method for measurably adjusting the semantics of text while preserving its sentiment and fluency, a task we call semantic text exchange. This is useful for text data augmentation and the semantic correction of text generated by chatbots and virtual assistants. We introduce a pipeline called SMERTI that combines entity replacement, similarity masking, and text infilling. We measure our pipeline's success by its Semantic Text Exchange Score (STES): the ability to preserve the original text's sentiment and fluency while adjusting semantic content. We propose to use masking (replacement) rate threshold as an adjustable parameter to control the amount of semantic change in the text. Our experiments demonstrate that SMERTI can outperform baseline models on Yelp reviews, Amazon reviews, and news headlines.