PyTorchKR Papers

최신 논문

총 1,749편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2411.09255공식 코드 · Papers with Code

DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine

We introduce DAHL, a benchmark dataset and automated evaluation system designed to assess hallucination in long-form text generation, specifically within the biomedical domain. Our benchmark dataset, meticulously curated from biomedical research papers, consists of 8,573 questions across 29 categories. DAHL evaluates fact-conflicting hallucinations in Large Language Models (LLMs) by deconstructing responses into atomic units, each representing a single piece of information. The accuracy of these responses is averaged to produce the DAHL Score, offering a more in-depth evaluation of hallucinations compared to previous methods that rely on multiple-choice tasks. We conduct experiments with 8 different models, finding that larger models tend to hallucinate less; however, beyond a model size of 7 to 8 billion parameters, further scaling does not significantly improve factual accuracy. The DAHL Score holds potential as an efficient alternative to human-annotated preference labels, being able to be expanded to other specialized domains. We release the dataset and code in public.

arXiv:2411.07854공식 코드 · Papers with Code

Tucano: Advancing Neural Text Generation for Portuguese

Significant advances have been made in natural language processing in recent years. However, our current deep learning approach to language modeling requires substantial resources in terms of data and computation. One of the side effects of this data-hungry paradigm is the current schism between languages, separating those considered high-resource, where most of the development happens and resources are available, and the low-resource ones, which struggle to attain the same level of performance and autonomy. This study aims to introduce a new set of resources to stimulate the future development of neural text generation in Portuguese. In this work, we document the development of GigaVerbo, a concatenation of deduplicated Portuguese text corpora amounting to 200 billion tokens. Via this corpus, we trained a series of decoder-transformers named Tucano. Our models perform equal or superior to other Portuguese and multilingual language models of similar size in several Portuguese benchmarks. The evaluation of our models also reveals that model performance on many currently available benchmarks used by the Portuguese NLP community has little to no correlation with the scaling of token ingestion during training, highlighting the limitations of such evaluations when it comes to the assessment of Portuguese generative language models. All derivatives of our study are openly released on GitHub and Hugging Face. See https://nkluge-correa.github.io/Tucano/

arXiv:2411.07122공식 코드 · Papers with Code

SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful content. This paper presents a novel approach to detect and steer concepts such as toxicity before generation. We introduce the Sparse Conditioned Autoencoder (SCAR), a single trained module that extends the otherwise untouched LLM. SCAR ensures full steerability, towards and away from concepts (e.g., toxic content), without compromising the quality of the model's text generation on standard evaluation benchmarks. We demonstrate the effective application of our approach through a variety of concepts, including toxicity, safety, and writing style alignment. As such, this work establishes a robust framework for controlling LLM generations, ensuring their ethical and safe deployment in real-world applications.

arXiv:2411.07127공식 코드 · Papers with Code

Benchmarking LLMs' Judgments with No Gold Standard

We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by Large Language Models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review. GEM uses a generative model to estimate mutual information between candidate and reference responses, without requiring the reference to be a gold standard. In experiments on a human-annotated dataset, GEM demonstrates competitive correlations with human scores compared to the state-of-the-art GPT-4o Examiner, and outperforms all other baselines. Additionally, GEM is more robust against strategic manipulations, such as rephrasing or elongation, which can artificially inflate scores under a GPT-4o Examiner. We also present GRE-bench (Generating Review Evaluation Benchmark) which evaluates LLMs based on how well they can generate high-quality peer reviews for academic research papers. Because GRE-bench is based upon GEM, it inherits its robustness properties. Additionally, GRE-bench circumvents data contamination problems (or data leakage) by using the continuous influx of new open-access research papers and peer reviews each year. We show GRE-bench results of various popular LLMs on their peer review capabilities using the ICLR2023 dataset.

arXiv:2411.06549공식 코드 · Papers with Code

In-Context Learning for Preserving Patient Privacy: A Framework for Synthesizing Realistic Patient Portal Messages

Since the COVID-19 pandemic, clinicians have seen a large and sustained influx in patient portal messages, significantly contributing to clinician burnout. To the best of our knowledge, there are no large-scale public patient portal messages corpora researchers can use to build tools to optimize clinician portal workflows. Informed by our ongoing work with a regional hospital, this study introduces an LLM-powered framework for configurable and realistic patient portal message generation. Our approach leverages few-shot grounded text generation, requiring only a small number of de-identified patient portal messages to help LLMs better match the true style and tone of real data. Clinical experts in our team deem this framework as HIPAA-friendly, unlike existing privacy-preserving approaches to synthetic text generation which cannot guarantee all sensitive attributes will be protected. Through extensive quantitative and human evaluation, we show that our framework produces data of higher quality than comparable generation methods as well as all related datasets. We believe this work provides a path forward for (i) the release of large-scale synthetic patient message datasets that are stylistically similar to ground-truth samples and (ii) HIPAA-friendly data generation which requires minimal human de-identification efforts.

arXiv:2411.06524공식 코드 · Papers with Code

Does This Summary Answer My Question? Modeling Query-Focused Summary Readers with Rational Speech Acts

Query-focused summarization (QFS) is the task of generating a summary in response to a user-written query. Despite its user-oriented nature, there has been limited work in QFS in explicitly considering a user's understanding of a generated summary, potentially causing QFS systems to underperform at inference time. In this paper, we adapt the Rational Speech Act (RSA) framework, a model of human communication, to explicitly model a reader's understanding of a query-focused summary and integrate it within the generation method of existing QFS systems. In particular, we introduce the answer reconstruction objective which approximates a reader's understanding of a summary by their ability to use it to reconstruct the answer to their initial query. Using this objective, we are able to re-rank candidate summaries generated by existing QFS systems and select summaries that better align with their corresponding query and reference summary. More generally, our study suggests that a simple and effective way of improving a language generation system designed for a user-centered task may be to explicitly incorporate its user requirements into the system's generation procedure.

arXiv:2411.05037공식 코드 · Papers with Code

Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop reasoning failures through targeted memory injections on LM attention heads. First, we analyze the per-layer activations of GPT-2 models in response to single- and multi-hop prompts. We then propose a mechanism that allows users to inject relevant prompt-specific information, which we refer to as "memories," at critical LM locations during inference. By thus enabling the LM to incorporate additional relevant information during inference, we enhance the quality of multi-hop prompt completions. We empirically show that a simple, efficient, and targeted memory injection into a key attention layer often increases the probability of the desired next token in multi-hop tasks, by up to 424%. We observe that small subsets of attention heads can significantly impact the model prediction during multi-hop reasoning. To more faithfully interpret these heads, we develop Attention Lens: an open source tool that translates the outputs of attention heads into vocabulary tokens via learned transformations called lenses. We demonstrate the use of lenses to reveal how a model arrives at its answer and use them to localize sources of model failures such as in the case of biased and malicious language generation.

arXiv:2411.03350cs.CL공식 코드 · Papers with Code

A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

대규모 언어 모델(LLM)의 발전은 자연어 처리 분야에서 혁신적인 변화를 가져왔으나, 이들 모델은 파라미터 크기와 계산 요구 사항으로 인해 실시간 응용 및 개인 정보 보호 문제를 야기하는 한계를 지니고 있다. 이러한 문제를 해결하기 위해 소형 언어 모델(SLM)의 필요성이 대두되었으며, SLM은 낮은 추론 지연 시간과 비용 효율성, 그리고 사용자 맞춤화의 용이성 덕분에 자원 제약 환경에서 특히 유용하다. 본 논문은 SLM의 정의, 획득, 응용, 향상 및 신뢰성에 대한 포괄적인 조사를 수행하여, SLM의 발전 방향을 제시하고자 한다. SLM의 정의는 다양하게 존재하지만, 본 연구에서는 전문 작업 수행 능력과 자원 제약 환경에 적합한 모델로 규정하고, 최소한의 크기와 자원 제약 하에서 지속 가능한 최대 크기를 기준으로 경계를 설정하였다. SLM의 아키텍처에 대한 분석을 통해 Transformer 아키텍처와 그 변형들이 SLM 성능에 미치는 영향을 논의하며, SLM을 처음부터 학습시키기 위한 다양한 기술도 소개한다. 특히, LLM에서 SLM으로 지식을 이전하는 방법으로 가지치기, 지식 증류, 양자화 기법을 다루어 SLM의 성능 향상 전략을 제시한다. SLM의 응용 분야는 광범위하며, 질문-응답 시스템, 코딩 작업, 추천 시스템 및 모바일 장치에서의 활용 사례를 통해 그 가능성을 탐구한다. 또한, SLM의 메모리 및 실행 시간 효율성을 최적화하는 기술을 통해 모바일 및 엣지 디바이스에의 배포 가능성도 강조된다. 마지막으로, SLM과 LLM 간의 시너지 효과를 통해 두 모델의 상호작용 및 협력 방안을 제안하며, SLM의 신뢰성을 높이기 위한 다양한 접근 방식을 논의한다. 이 논문은 SLM의 발전을 위한 체계적인 프레임워크를 제시하며, LLM의 한계를 극복하고 다양한 응용 분야에서의 활용 가능성을 높이는 데 기여할 것으로 기대된다.

arXiv:2411.03806공식 코드 · Papers with Code

Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection

Natural Language Generation has been rapidly developing with the advent of large language models (LLMs). While their usage has sparked significant attention from the general public, it is important for readers to be aware when a piece of text is LLM-generated. This has brought about the need for building models that enable automated LLM-generated text detection, with the aim of mitigating potential negative outcomes of such content. Existing LLM-generated detectors show competitive performances in telling apart LLM-generated and human-written text, but this performance is likely to deteriorate when paraphrased texts are considered. In this study, we devise a new data collection strategy to collect Human & LLM Paraphrase Collection (HLPC), a first-of-its-kind dataset that incorporates human-written texts and paraphrases, as well as LLM-generated texts and paraphrases. With the aim of understanding the effects of human-written paraphrases on the performance of state-of-the-art LLM-generated text detectors OpenAI RoBERTa and watermark detectors, we perform classification experiments that incorporate human-written paraphrases, watermarked and non-watermarked LLM-generated documents from GPT and OPT, and LLM-generated paraphrases from DIPPER and BART. The results show that the inclusion of human-written paraphrases has a significant impact of LLM-generated detector performance, promoting TPR@1%FPR with a possible trade-off of AUROC and accuracy.

arXiv:2411.02448공식 코드 · Papers with Code

Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models

LLMs have demonstrated impressive proficiency in generating coherent and high-quality text, making them valuable across a range of text-generation tasks. However, rigorous evaluation of this generated content is crucial, as ensuring its quality remains a significant challenge due to persistent issues such as factual inaccuracies and hallucination. This paper introduces three fine-tuned general-purpose LLM autoevaluators, REC-8B, REC-12B and REC-70B, specifically designed to evaluate generated text across several dimensions: faithfulness, instruction following, coherence, and completeness. These models not only provide ratings for these metrics but also offer detailed explanation and verifiable citation, thereby enhancing trust in the content. Moreover, the models support various citation modes, accommodating different requirements for latency and granularity. Extensive evaluations on diverse benchmarks demonstrate that our general-purpose LLM auto-evaluator, REC-70B, outperforms state-of-the-art LLMs, excelling in content evaluation by delivering better quality explanation and citation with minimal bias. Our REC dataset and models are available at https://github.com/adelaidehsu/REC.

arXiv:2411.01710공식 코드 · Papers with Code

SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation

Spurred by the demand for interpretable models, research on eXplainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP explored such methods for classification tasks and textual applications, explainability intersecting generation and speech is lagging, with existing techniques failing to account for the autoregressive nature of state-of-the-art models and to provide fine-grained, phonetically meaningful explanations. We address this gap by introducing Spectrogram Perturbation for Explainable Speech-to-text Generation (SPES), a feature attribution technique applicable to sequence generation tasks with autoregressive models. SPES provides explanations for each predicted token based on both the input spectrogram and the previously generated tokens. Extensive evaluation on speech recognition and translation demonstrates that SPES generates explanations that are faithful and plausible to humans.

arXiv:2411.01610공식 코드 · Papers with Code

Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM

Contrastive decoding (CD) (Li et al., 2023) improves the next-token distribution of a large expert language model (LM) using a small amateur LM. Although CD is applied to various LMs and domains to enhance open-ended text generation, it is still unclear why CD often works well, when it could fail, and how we can make it better. To deepen our understanding of CD, we first theoretically prove that CD could be viewed as linearly extrapolating the next-token logits from a huge and hypothetical LM. We also highlight that the linear extrapolation could make CD unable to output the most obvious answers that have already been assigned high probabilities by the amateur LM. To overcome CD's limitation, we propose a new unsupervised decoding method called $\mathbf{A}$symptotic $\mathbf{P}$robability $\mathbf{D}$ecoding (APD). APD explicitly extrapolates the probability curves from the LMs of different sizes to infer the asymptotic probabilities from an infinitely large LM without inducing more inference costs than CD. In FactualityPrompts, an open-ended text generation benchmark, sampling using APD significantly boosts factuality in comparison to the CD sampling and its variants, and achieves state-of-the-art results for Pythia 6.9B and OPT 6.7B. Furthermore, in five commonsense QA datasets, APD is often significantly better than CD and achieves a similar effect of using a larger LLM. For example, the perplexity of APD on top of Pythia 6.9B is even lower than the perplexity of Pythia 12B in CommonsenseQA and LAMBADA.

arXiv:2411.02083공식 코드 · Papers with Code

Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models

While language models have exceptional capabilities at text generation, they lack a natural inductive bias for emitting numbers and thus struggle in tasks involving quantitative reasoning, especially arithmetic. One fundamental limitation is the nature of the Cross Entropy loss, which assumes a nominal scale and thus cannot convey proximity between generated number tokens. In response, we here present a regression-like loss that operates purely on token level. Our proposed Number Token Loss (NTL) comes in two flavors and minimizes either the Lp norm or the Wasserstein distance between the numerical values of the real and predicted number tokens. NTL can easily be added to any language model and extend the Cross Entropy objective during training without runtime overhead. We evaluate the proposed scheme on various mathematical datasets and find that it consistently improves performance in math-related tasks. In a direct comparison on a regression task, we find that NTL can match the performance of a regression head, despite operating on token level. Finally, we scale NTL up to 3B parameter models and observe improved performance, demonstrating its potential for seamless integration into LLMs. We hope that this work can inspire LLM developers to improve their pretraining objectives. The code is available via: https://tum-ai.github.io/number-token-loss/

arXiv:2410.23933공식 코드 · Papers with Code

Language Models can Self-Lengthen to Generate Long Texts

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where pre-training lacks effective instructions for long-text generation, and post-training data primarily consists of short query-response pairs. Current approaches, such as instruction backtranslation and behavior imitation, face challenges including data quality, copyright issues, and constraints on proprietary model usage. In this paper, we introduce an innovative iterative training framework called Self-Lengthen that leverages only the intrinsic knowledge and skills of LLMs without the need for auxiliary data or proprietary models. The framework consists of two roles: the Generator and the Extender. The Generator produces the initial response, which is then split and expanded by the Extender. This process results in a new, longer response, which is used to train both the Generator and the Extender iteratively. Through this process, the models are progressively trained to handle increasingly longer responses. Experiments on benchmarks and human evaluations show that Self-Lengthen outperforms existing methods in long-text generation, when applied to top open-source LLMs such as Qwen2 and LLaMA3. Our code is publicly available at https://github.com/QwenLM/Self-Lengthen.

arXiv:2410.22971공식 코드 · Papers with Code

Private Synthetic Text Generation with Diffusion Models

How capable are diffusion models of generating synthetics texts? Recent research shows their strengths, with performance reaching that of auto-regressive LLMs. But are they also good in generating synthetic data if the training was under differential privacy? Here the evidence is missing, yet the promises from private image generation look strong. In this paper we address this open question by extensive experiments. At the same time, we critically assess (and reimplement) previous works on synthetic private text generation with LLMs and reveal some unmet assumptions that might have led to violating the differential privacy guarantees. Our results partly contradict previous non-private findings and show that fully open-source LLMs outperform diffusion models in the privacy regime. Our complete source codes, datasets, and experimental setup is publicly available to foster future research.

arXiv:2410.22660공식 코드 · Papers with Code

Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models

Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP). Most existing research focuses on either syntactic constraints or neural generation, with few efforts to integrate linguistic theory with large language models (LLMs) for generating natural code-switched text. In this paper, we introduce EZSwitch, a novel framework that combines Equivalence Constraint Theory (ECT) with LLMs to produce linguistically valid and fluent code-switched text. We evaluate our method using both human judgments and automatic metrics, demonstrating a significant improvement in the quality of generated code-switching sentences compared to baseline LLMs. To address the lack of suitable evaluation metrics, we conduct a comprehensive correlation study of various automatic metrics against human scores, revealing that current metrics often fail to capture the nuanced fluency of code-switched text. Additionally, we create CSPref, a human preference dataset based on human ratings and analyze model performance across ``hard`` and ``easy`` examples. Our findings indicate that incorporating linguistic constraints into LLMs leads to more robust and human-aligned generation, paving the way for scalable code-switching text generation across diverse language pairs.

arXiv:2410.20916공식 코드 · Papers with Code

NeuGPT: Unified multi-modal Neural GPT

This paper introduces NeuGPT, a groundbreaking multi-modal language generation model designed to harmonize the fragmented landscape of neural recording research. Traditionally, studies in the field have been compartmentalized by signal type, with EEG, MEG, ECoG, SEEG, fMRI, and fNIRS data being analyzed in isolation. Recognizing the untapped potential for cross-pollination and the adaptability of neural signals across varying experimental conditions, we set out to develop a unified model capable of interfacing with multiple modalities. Drawing inspiration from the success of pre-trained large models in NLP, computer vision, and speech processing, NeuGPT is architected to process a diverse array of neural recordings and interact with speech and text data. Our model mainly focus on brain-to-text decoding, improving SOTA from 6.94 to 12.92 on BLEU-1 and 6.93 to 13.06 on ROUGE-1F. It can also simulate brain signals, thereby serving as a novel neural interface. Code is available at \href{https://github.com/NeuSpeech/NeuGPT}{NeuSpeech/NeuGPT (https://github.com/NeuSpeech/NeuGPT) .}

arXiv:2410.20022공식 코드 · Papers with Code

Dynamic layer selection in decoder-only transformers

The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-at-hand to reduce the overall computational cost. We empirically examine two common dynamic inference methods for natural language generation (NLG): layer skipping and early exiting. We find that a pre-trained decoder-only model is significantly more robust to layer removal via layer skipping, as opposed to early exit. We demonstrate the difficulty of using hidden state information to adapt computation on a per-token basis for layer skipping. Finally, we show that dynamic computation allocation on a per-sequence basis holds promise for significant efficiency gains by constructing an oracle controller. Remarkably, we find that there exists an allocation which achieves equal performance to the full model using only 23.3% of its layers on average.

arXiv:2410.20783공식 코드 · Papers with Code

Graph-based Uncertainty Metrics for Long-form Language Model Outputs

Recent advancements in Large Language Models (LLMs) have significantly improved text generation capabilities, but these systems are still known to hallucinate, and granular uncertainty estimation for long-form LLM generations remains challenging. In this work, we propose Graph Uncertainty -- which represents the relationship between LLM generations and claims within them as a bipartite graph and estimates the claim-level uncertainty with a family of graph centrality metrics. Under this view, existing uncertainty estimation methods based on the concept of self-consistency can be viewed as using degree centrality as an uncertainty measure, and we show that more sophisticated alternatives such as closeness centrality provide consistent gains at claim-level uncertainty estimation. Moreover, we present uncertainty-aware decoding techniques that leverage both the graph structure and uncertainty estimates to improve the factuality of LLM generations by preserving only the most reliable claims. Compared to existing methods, our graph-based uncertainty metrics lead to an average of 6.8% relative gains on AUPRC across various long-form generation settings, and our end-to-end system provides consistent 2-4% gains in factuality over existing decoding techniques while significantly improving the informativeness of generated responses.

arXiv:2410.19222공식 코드 · Papers with Code

Peptide-GPT: Generative Design of Peptides using Generative Pre-trained Transformers and Bio-informatic Supervision

In recent years, natural language processing (NLP) models have demonstrated remarkable capabilities in various domains beyond traditional text generation. In this work, we introduce PeptideGPT, a protein language model tailored to generate protein sequences with distinct properties: hemolytic activity, solubility, and non-fouling characteristics. To facilitate a rigorous evaluation of these generated sequences, we established a comprehensive evaluation pipeline consisting of ideas from bioinformatics to retain valid proteins with ordered structures. First, we rank the generated sequences based on their perplexity scores, then we filter out those lying outside the permissible convex hull of proteins. Finally, we predict the structure using ESMFold and select the proteins with pLDDT values greater than 70 to ensure ordered structure. The properties of generated sequences are evaluated using task-specific classifiers - PeptideBERT and HAPPENN. We achieved an accuracy of 76.26% in hemolytic, 72.46% in non-hemolytic, 78.84% in non-fouling, and 68.06% in solubility protein generation. Our experimental results demonstrate the effectiveness of PeptideGPT in de novo protein design and underscore the potential of leveraging NLP-based approaches for paving the way for future innovations and breakthroughs in synthetic biology and bioinformatics. Codes, models, and data used in this study are freely available at: https://github.com/aayush-shah14/PeptideGPT.