PyTorchKR Papers

최신 논문

총 1,749편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.12212공식 코드 · Papers with Code

Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset

Since 2018, when the Transformer architecture was introduced, Natural Language Processing has gained significant momentum with pre-trained Transformer-based models that can be fine-tuned for various tasks. Most models are pre-trained on large English corpora, making them less applicable to other languages, such as Brazilian Portuguese. In our research, we identified two models pre-trained in Brazilian Portuguese (BERTimbau and PTT5) and two multilingual models (mBERT and mT5). BERTimbau and mBERT use only the Encoder module, while PTT5 and mT5 use both the Encoder and Decoder. Our study aimed to evaluate their performance on a financial Named Entity Recognition (NER) task and determine the computational requirements for fine-tuning and inference. To this end, we developed the Brazilian Financial NER (BraFiNER) dataset, comprising sentences from Brazilian banks' earnings calls transcripts annotated using a weakly supervised approach. Additionally, we introduced a novel approach that reframes the token classification task as a text generation problem. After fine-tuning the models, we evaluated them using performance and error metrics. Our findings reveal that BERT-based models consistently outperform T5-based models. While the multilingual models exhibit comparable macro F1-scores, BERTimbau demonstrates superior performance over PTT5. In terms of error metrics, BERTimbau outperforms the other models. We also observed that PTT5 and mT5 generated sentences with changes in monetary and percentage values, highlighting the importance of accuracy and consistency in the financial domain. Our findings provide insights into the differing performance of BERT- and T5-based models for the NER task.

arXiv:2403.11747공식 코드 · Papers with Code

Embedded Named Entity Recognition using Probing Classifiers

Streaming text generation has become a common way of increasing the responsiveness of language model powered applications, such as chat assistants. At the same time, extracting semantic information from generated text is a useful tool for applications such as automated fact checking or retrieval augmented generation. Currently, this requires either separate models during inference, which increases computational cost, or destructive fine-tuning of the language model. Instead, we propose an approach called EMBER which enables streaming named entity recognition in decoder-only language models without fine-tuning them and while incurring minimal additional computational cost at inference time. Specifically, our experiments show that EMBER maintains high token generation rates, with only a negligible decrease in speed of around 1% compared to a 43.64% slowdown measured for a baseline. We make our code and data available online, including a toolkit for training, testing, and deploying efficient token classification models optimized for streaming text generation.

arXiv:2403.11335공식 코드 · Papers with Code

ConvSDG: Session Data Generation for Conversational Search

Conversational search provides a more convenient interface for users to search by allowing multi-turn interaction with the search engine. However, the effectiveness of the conversational dense retrieval methods is limited by the scarcity of training data required for their fine-tuning. Thus, generating more training conversational sessions with relevant labels could potentially improve search performance. Based on the promising capabilities of large language models (LLMs) on text generation, we propose ConvSDG, a simple yet effective framework to explore the feasibility of boosting conversational search by using LLM for session data generation. Within this framework, we design dialogue/session-level and query-level data generation with unsupervised and semi-supervised learning, according to the availability of relevance judgments. The generated data are used to fine-tune the conversational dense retriever. Extensive experiments on four widely used datasets demonstrate the effectiveness and broad applicability of our ConvSDG framework compared with several strong baselines.

arXiv:2403.11558공식 코드 · Papers with Code

Reinforcement Learning with Token-level Feedback for Controllable Text Generation

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel reinforcement learning algorithm named TOLE which formulates TOken-LEvel rewards for controllable text generation, and employs a "first-quantize-then-noise" paradigm to enhance the robustness of the RL algorithm.Furthermore, TOLE can be flexibly extended to multiple constraints with little computational expense. Experimental results show that our algorithm can achieve superior performance on both single-attribute and multi-attribute control tasks. We have released our codes at https://github.com/WindyLee0822/CTG

arXiv:2403.10081공식 코드 · Papers with Code

DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's real-time information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the real-time Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method. We have open-sourced all the code, data, and models in GitHub: https://github.com/oneal2000/DRAGIN/tree/main

arXiv:2403.10266공식 코드 · Papers with Code

DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers

Scaling multi-dimensional transformers to long sequences is indispensable across various domains. However, the challenges of large memory requirements and slow speeds of such sequences necessitate sequence parallelism. All existing approaches fall under the category of embedded sequence parallelism, which are limited to shard along a single sequence dimension, thereby introducing significant communication overhead. However, the nature of multi-dimensional transformers involves independent calculations across multiple sequence dimensions. To this end, we propose Dynamic Sequence Parallelism (DSP) as a novel abstraction of sequence parallelism. DSP dynamically switches the parallel dimension among all sequences according to the computation stage with efficient resharding strategy. DSP offers significant reductions in communication costs, adaptability across modules, and ease of implementation with minimal constraints. Experimental evaluations demonstrate DSP's superiority over state-of-the-art embedded sequence parallelism methods by remarkable throughput improvements ranging from 32.2% to 10x, with less than 25% communication volume.

arXiv:2403.09054공식 코드 · Papers with Code

Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which constitutes the majority of the computational workload, primarily entails vector-matrix multiplications and interactions with the Key-Value (KV) Cache. This phase is constrained by memory bandwidth due to the overhead of transferring weights and KV cache values from the memory system to the computing units. This memory bottleneck becomes particularly pronounced in applications that require long-context and extensive text generation, both of which are increasingly crucial for LLMs. This paper introduces "Keyformer", an innovative inference-time approach, to mitigate the challenges associated with KV cache size and memory bandwidth utilization. Keyformer leverages the observation that approximately 90% of the attention weight in generative inference focuses on a specific subset of tokens, referred to as "key" tokens. Keyformer retains only the key tokens in the KV cache by identifying these crucial tokens using a novel score function. This approach effectively reduces both the KV cache size and memory bandwidth usage without compromising model accuracy. We evaluate Keyformer's performance across three foundational models: GPT-J, Cerebras-GPT, and MPT, which employ various positional embedding algorithms. Our assessment encompasses a variety of tasks, with a particular emphasis on summarization and conversation tasks involving extended contexts. Keyformer's reduction of KV cache reduces inference latency by 2.1x and improves token generation throughput by 2.4x, while preserving the model's accuracy.

arXiv:2403.08293공식 코드 · Papers with Code

Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale

A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being pre-trained from scratch on raw texts with high parallelism. GPST circumvents the limitations of previous SLMs such as relying on gold trees and sequential training. It consists of two components, a usual SLM supervised by a uni-directional language modeling loss, and an additional composition model, which induces syntactic parse trees and computes constituent representations, supervised by a bi-directional language modeling loss. We propose a representation surrogate to enable joint parallel training of the two models in a hard-EM fashion. We pre-train GPST on OpenWebText, a corpus with $9$ billion tokens, and demonstrate the superiority of GPST over GPT-2 with a comparable size in numerous tasks covering both language understanding and language generation. Meanwhile, GPST also significantly outperforms existing unsupervised SLMs on left-to-right grammar induction, while holding a substantial acceleration on training.

arXiv:2403.07567공식 코드 · Papers with Code

Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation

Most data-to-text datasets are for English, so the difficulties of modelling data-to-text for low-resource languages are largely unexplored. In this paper we tackle data-to-text for isiXhosa, which is low-resource and agglutinative. We introduce Triples-to-isiXhosa (T2X), a new dataset based on a subset of WebNLG, which presents a new linguistic context that shifts modelling demands to subword-driven techniques. We also develop an evaluation framework for T2X that measures how accurately generated text describes the data. This enables future users of T2X to go beyond surface-level metrics in evaluation. On the modelling side we explore two classes of methods - dedicated data-to-text models trained from scratch and pretrained language models (PLMs). We propose a new dedicated architecture aimed at agglutinative data-to-text, the Subword Segmental Pointer Generator (SSPG). It jointly learns to segment words and copy entities, and outperforms existing dedicated models for 2 agglutinative languages (isiXhosa and Finnish). We investigate pretrained solutions for T2X, which reveals that standard PLMs come up short. Fine-tuning machine translation models emerges as the best method overall. These findings underscore the distinct challenge presented by T2X: neither well-established data-to-text architectures nor customary pretrained methodologies prove optimal. We conclude with a qualitative analysis of generation errors and an ablation study.

arXiv:2403.07556공식 코드 · Papers with Code

Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts

Although Large Language Models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. To alleviate LLMs from being misled by untruthful context and take advantage of knowledge augmentation, we propose Truth-Aware Context Selection (TACS), a lightweight method to adaptively recognize and mask untruthful context from the inputs. TACS begins by performing truth detection on the input context, leveraging the parameterized knowledge within the LLM. Subsequently, it constructs a corresponding attention mask based on the truthfulness of each position, selecting the truthful context and discarding the untruthful context. Additionally, we introduce a new evaluation metric, Disturbance Adaption Rate, to further study the LLMs' ability to accept truthful information and resist untruthful information. Experimental results indicate that TACS can effectively filter untruthful context and significantly improve the overall quality of LLMs' responses when presented with misleading information.

arXiv:2403.07369공식 코드 · Papers with Code

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery

In this paper, we study the problem of Generalized Category Discovery (GCD), which aims to cluster unlabeled data from both known and unknown categories using the knowledge of labeled data from known categories. Current GCD methods rely on only visual cues, which however neglect the multi-modality perceptive nature of human cognitive processes in discovering novel visual categories. To address this, we propose a two-phase TextGCD framework to accomplish multi-modality GCD by exploiting powerful Visual-Language Models. TextGCD mainly includes a retrieval-based text generation (RTG) phase and a cross-modality co-teaching (CCT) phase. First, RTG constructs a visual lexicon using category tags from diverse datasets and attributes from Large Language Models, generating descriptive texts for images in a retrieval manner. Second, CCT leverages disparities between textual and visual modalities to foster mutual learning, thereby enhancing visual GCD. In addition, we design an adaptive class aligning strategy to ensure the alignment of category perceptions between modalities as well as a soft-voting mechanism to integrate multi-modality cues. Experiments on eight datasets show the large superiority of our approach over state-of-the-art methods. Notably, our approach outperforms the best competitor, by 7.7% and 10.8% in All accuracy on ImageNet-1k and CUB, respectively.

arXiv:2403.07398공식 코드 · Papers with Code

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scarcity makes it challenging for language models to learn to generate commonsense inferences for contexts and questions involving interactions between complex events. To address this demand, we present COM2 (COMplex COMmonsense), a new dataset created by sampling multi-hop logical queries (e.g., the joint effect or cause of both event A and B, or the effect of the effect of event C) from an existing commonsense knowledge graph (CSKG), and verbalizing them using handcrafted rules and large language models into multiple-choice and text generation questions. Our experiments show that language models trained on COM2 exhibit significant improvements in complex reasoning ability, resulting in enhanced zero-shot performance in both in-domain and out-of-domain tasks for question answering and generative commonsense reasoning, without expensive human annotations. Code and data are available at https://github.com/tqfang/complex-commonsense-reasoning.

arXiv:2403.05973공식 코드 · Papers with Code

Calibrating Large Language Models Using Their Generations Only

As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model's confidence in its prediction becomes even more important. However, finding effective ways to calibrate LLMs - especially when the only interface to the models is their generated text - remains a challenge. We propose APRICOT (auxiliary prediction of confidence targets): A method to set confidence targets and train an additional model that predicts an LLM's confidence based on its textual input and output alone. This approach has several advantages: It is conceptually simple, does not require access to the target model beyond its output, does not interfere with the language generation, and has a multitude of potential usages, for instance by verbalizing the predicted confidence or adjusting the given answer based on the confidence. We show how our approach performs competitively in terms of calibration error for white-box and black-box LLMs on closed-book question-answering to detect incorrect LLM answers.

arXiv:2403.06754공식 코드 · Papers with Code

ALaRM: Align Language Models via Hierarchical Rewards Modeling

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework addresses the limitations of current alignment approaches, which often struggle with the inconsistency and sparsity of human supervision signals, by integrating holistic rewards with aspect-specific rewards. This integration enables more precise and consistent guidance of language models towards desired outcomes, particularly in complex and open text generation tasks. By employing a methodology that filters and combines multiple rewards based on their consistency, the framework provides a reliable mechanism for improving model alignment. We validate our approach through applications in long-form question answering and machine translation tasks, employing gpt-3.5-turbo for pairwise comparisons, and demonstrate improvements over existing baselines. Our work underscores the effectiveness of hierarchical rewards modeling in refining LLM training processes for better human preference alignment. We release our code at https://ALaRM-fdu.github.io.

arXiv:2403.04811공식 코드 · Papers with Code

Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models

While large language models have achieved remarkable performance on various code generation benchmarks, there have been growing concerns regarding potential contamination of these benchmarks as they may be leaked into pretraining and finetuning data. While recent work has investigated contamination in natural language generation and understanding tasks, there has been less extensive research into how data contamination impacts the evaluation of code generation, which is critical for understanding the robustness and reliability of LLMs in programming contexts. In this work, we perform a comprehensive study of data contamination of popular code generation benchmarks, and precisely quantify their overlap with pretraining corpus through both surface-level and semantic-level matching. In our experiments, we show that there are substantial overlap between popular code generation benchmarks and open training corpus, and models perform significantly better on the subset of the benchmarks where similar solutions are seen during training. We also conduct extensive analysis on the factors that affects model memorization and generalization, such as model size, problem difficulty, and question length. We release all resulting files from our matching pipeline for future research.

arXiv:2403.05030공식 코드 · Papers with Code

Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively search for inputs that may elicit harmful behaviors. Red-teaming and adversarial training (AT) are commonly used to improve robustness, however, they empirically struggle to fix failure modes that differ from the attacks used during training. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without leveraging knowledge of what they are or using inputs that elicit them. LAT makes use of the compressed, abstract, and structured latent representations of concepts that the network actually uses for prediction. Here, we use it to defend against failure modes without examples that elicit them. Specifically, we use LAT to remove trojans and defend against held-out classes of adversarial attacks. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness to novel attacks and performance on clean data relative to AT. This suggests that LAT can be a promising tool for defending against failure modes that are not explicitly identified by developers.

arXiv:2403.04643공식 코드 · Papers with Code

QAQ: Quality Adaptive Quantization for LLM KV Cache

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model deployment emerges due to the linear expansion of the Key-Value (KV) cache with the context length. Existing methods primarily rely on various hypotheses, such as sorting the KV cache based on attention scores for replacement or eviction, to compress the KV cache and improve model throughput. However, heuristics used by these strategies may wrongly evict essential KV cache, which can significantly degrade model performance. In this paper, we propose QAQ, a Quality Adaptive Quantization scheme for the KV cache. We theoretically demonstrate that key cache and value cache exhibit distinct sensitivities to quantization, leading to the formulation of separate quantization strategies for their non-uniform quantization. Through the integration of dedicated outlier handling, as well as an improved attention-aware approach, QAQ achieves up to 10x the compression ratio of the KV cache size with a neglectable impact on model performance. QAQ significantly reduces the practical hurdles of deploying LLMs, opening up new possibilities for longer-context applications. The code is available at github.com/ClubieDong/KVCacheQuantization.

arXiv:2403.04366공식 코드 · Papers with Code

Enhancing Court View Generation with Knowledge Injection and Guidance

Court View Generation (CVG) is a challenging task in the field of Legal Artificial Intelligence (LegalAI), which aims to generate court views based on the plaintiff claims and the fact descriptions. While Pretrained Language Models (PLMs) have showcased their prowess in natural language generation, their application to the complex, knowledge-intensive domain of CVG often reveals inherent limitations. In this paper, we present a novel approach, named Knowledge Injection and Guidance (KIG), designed to bolster CVG using PLMs. To efficiently incorporate domain knowledge during the training stage, we introduce a knowledge-injected prompt encoder for prompt tuning, thereby reducing computational overhead. Moreover, to further enhance the model's ability to utilize domain knowledge, we employ a generating navigator, which dynamically guides the text generation process in the inference stage without altering the model's architecture, making it readily transferable. Comprehensive experiments on real-world data demonstrate the effectiveness of our approach compared to several established baselines, especially in the responsivity of claims, where it outperforms the best baseline by 11.87%.

arXiv:2403.03585공식 코드 · Papers with Code

RouteExplainer: An Explanation Framework for Vehicle Routing Problem

The Vehicle Routing Problem (VRP) is a widely studied combinatorial optimization problem and has been applied to various practical problems. While the explainability for VRP is significant for improving the reliability and interactivity in practical VRP applications, it remains unexplored. In this paper, we propose RouteExplainer, a post-hoc explanation framework that explains the influence of each edge in a generated route. Our framework realizes this by rethinking a route as the sequence of actions and extending counterfactual explanations based on the action influence model to VRP. To enhance the explanation, we additionally propose an edge classifier that infers the intentions of each edge, a loss function to train the edge classifier, and explanation-text generation by Large Language Models (LLMs). We quantitatively evaluate our edge classifier on four different VRPs. The results demonstrate its rapid computation while maintaining reasonable accuracy, thereby highlighting its potential for deployment in practical applications. Moreover, on the subject of a tourist route, we qualitatively evaluate explanations generated by our framework. This evaluation not only validates our framework but also shows the synergy between explanation frameworks and LLMs. See https://ntt-dkiku.github.io/xai-vrp for our code, datasets, models, and demo.

arXiv:2403.00932공식 코드 · Papers with Code

Differentially Private Knowledge Distillation via Synthetic Text Generation

Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practitioners to train LLMs with Differential Privacy (DP) on private data. Concurrently, the exponential growth in parameter size of LLMs necessitates model compression before deployment of LLMs on resource-constrained devices or latency-sensitive applications. Differential privacy and model compression generally must trade off utility loss to achieve their objectives. Moreover, simultaneously applying both schemes can compound the utility degradation. To this end, we propose DistilDP: a novel differentially private knowledge distillation algorithm that exploits synthetic data generated by a differentially private teacher LLM. The knowledge of a teacher LLM is transferred onto the student in two ways: one way from the synthetic data itself -- the hard labels, and the other way by the output distribution of the teacher evaluated on the synthetic data -- the soft labels. Furthermore, if the teacher and student share a similar architectural structure, we can further distill knowledge by aligning the hidden representations between both. Our experimental results demonstrate that DistilDP can substantially improve the utility over existing baselines, at least $9.0$ PPL on the Big Patent dataset, with strong privacy parameters, $\epsilon=2$. These promising results progress privacy-preserving compression of autoregressive LLMs. Our code can be accessed here: https://github.com/james-flemings/dp_compress.