PyTorchKR Papers

최신 논문

총 40편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.00633

Self-Evaluation Guided Beam Search for Reasoning

Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging to elicit accurate final results. To tackle this challenge of uncertainty in multi-step reasoning, we introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of LLMs. We propose a decoding algorithm integrating the self-evaluation guidance via stochastic beam search. The self-evaluation guidance serves as a better-calibrated automatic criterion, facilitating an efficient search in the reasoning space and resulting in superior prediction quality. Stochastic beam search balances exploitation and exploration of the search space with temperature-controlled randomness. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34\%$, $9.56\%$, and $5.46\%$ on the GSM8K, AQuA, and StrategyQA benchmarks, respectively. Experiment results with Llama-2 on arithmetic reasoning demonstrate the efficiency of our method in outperforming the baseline methods with comparable computational budgets. Further analysis in multi-step reasoning finds our self-evaluation guidance pinpoints logic failures and leads to higher consistency and robustness. Our code is publicly available at https://guideddecoding.github.io/.

arXiv:2305.18395공식 코드 · Papers with Code

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be challenging due to their high computational requirements and concerns on data privacy. Previous studies have focused on building task-specific small Language Models (LMs) by fine-tuning them with labeled data or distilling LLMs. However, these approaches are ill-suited for knowledge-intensive reasoning tasks due to the limited capacity of small LMs in memorizing the knowledge required. Motivated by our theoretical analysis on memorization, we propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales obtained from LLMs with augmented knowledge retrieved from an external knowledge base. Moreover, we further propose a neural reranker to obtain documents relevant to rationale generation. We empirically show that KARD significantly improves the performance of small T5 and GPT models on the challenging knowledge-intensive reasoning datasets, namely MedQA-USMLE, StrategyQA, and OpenbookQA. Notably, our method makes the 250M T5 models achieve superior performance against the fine-tuned 3B models, having 12 times larger parameters, on both MedQA-USMLE and StrategyQA benchmarks.

arXiv:2311.18397

IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions

Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for open-domain QA tasks. However, common knowledge bases are inherently constrained by limited coverage and noisy information, making retrieval-based approaches inadequate to answer implicit reasoning questions. In this paper, we propose an Induction-Augmented Generation (IAG) framework that utilizes inductive knowledge along with the retrieved documents for implicit reasoning. We leverage large language models (LLMs) for deriving such knowledge via a novel prompting method based on inductive reasoning patterns. On top of this, we implement two versions of IAG named IAG-GPT and IAG-Student, respectively. IAG-GPT directly utilizes the knowledge generated by GPT-3 for answer prediction, while IAG-Student gets rid of dependencies on GPT service at inference time by incorporating a student inductor model. The inductor is firstly trained via knowledge distillation and further optimized by back-propagating the generator feedback via differentiable beam scores. Experimental results show that IAG outperforms RAG baselines as well as ChatGPT on two Open-Domain QA tasks. Notably, our best models have won the first place in the official leaderboards of CSQA2.0 (since Nov 1, 2022) and StrategyQA (since Jan 8, 2023).

arXiv:2311.07961

The ART of LLM Refinement: Ask, Refine, and Trust

In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and correct the errors in their generations when asked to do so. However, recent empirical evidence points in the opposite direction, suggesting that LLMs often struggle to accurately identify errors when reasoning is involved. To address this, we propose a reasoning with refinement objective called ART: Ask, Refine, and Trust, which asks necessary questions to decide when an LLM should refine its output, and either affirm or withhold trust in its refinement by ranking the refinement and the initial prediction. On two multistep reasoning tasks of mathematical word problems (GSM8K) and question answering (StrategyQA), ART achieves a performance gain of +5 points over self-refinement baselines, while using a much smaller model as the decision maker. We also demonstrate the benefit of using smaller models to make refinement decisions as a cost-effective alternative to fine-tuning a larger model.

arXiv:2311.02805공식 코드 · Papers with Code

Tailoring Self-Rationalizers with Multi-Reward Distillation

Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant scales (e.g., 175B parameter GPT-3); and 2) focuses largely on downstream performance, ignoring the semantics of the rationales themselves, e.g., are they faithful, true, and helpful for humans? In this work, we enable small-scale LMs (approx. 200x smaller than GPT-3) to generate rationales that not only improve downstream task performance, but are also more plausible, consistent, and diverse, assessed both by automatic and human evaluation. Our method, MaRio (Multi-rewArd RatIOnalization), is a multi-reward conditioned self-rationalization algorithm that optimizes multiple distinct properties like plausibility, diversity and consistency. Results on five difficult question-answering datasets StrategyQA, QuaRel, OpenBookQA, NumerSense and QASC show that not only does MaRio improve task accuracy, but it also improves the self-rationalization quality of small LMs across the aforementioned axes better than a supervised fine-tuning (SFT) baseline. Extensive human evaluations confirm that MaRio rationales are preferred vs. SFT rationales, as well as qualitative improvements in plausibility and consistency.

arXiv:2310.00194공식 코드 · Papers with Code

Improving Planning with Large Language Models: A Modular Agentic Architecture

Large language models (LLMs) demonstrate impressive performance on a wide variety of tasks, but they often struggle with tasks that require multi-step reasoning or goal-directed planning. Both cognitive neuroscience and reinforcement learning (RL) have proposed a number of interacting functional components that together implement search and evaluation in multi-step decision making. These components include conflict monitoring, state prediction, state evaluation, task decomposition, and orchestration. To improve planning with LLMs, we propose an agentic architecture, the Modular Agentic Planner (MAP), in which planning is accomplished via the recurrent interaction of the specialized modules mentioned above, each implemented using an LLM. MAP improves planning through the interaction of specialized modules that break down a larger problem into multiple brief automated calls to the LLM. We evaluate MAP on three challenging planning tasks -- graph traversal, Tower of Hanoi, and the PlanBench benchmark -- as well as an NLP task requiring multi-step reasoning (strategyQA). We find that MAP yields significant improvements over both standard LLM methods (zero-shot prompting, in-context learning) and competitive baselines (chain-of-thought, multi-agent debate, and tree-of-thought), can be effectively combined with smaller and more cost-efficient LLMs (Llama3-70B), and displays superior transfer across tasks. These results suggest the benefit of a modular and multi-agent approach to planning with LLMs.

arXiv:2309.13165

Large Language Models Are Also Good Prototypical Commonsense Reasoners

Commonsense reasoning is a pivotal skill for large language models, yet it presents persistent challenges in specific tasks requiring this competence. Traditional fine-tuning approaches can be resource-intensive and potentially compromise a model's generalization capacity. Furthermore, state-of-the-art language models like GPT-3.5 and Claude are primarily accessible through API calls, which makes fine-tuning models challenging. To address these challenges, we draw inspiration from the outputs of large models for tailored tasks and semi-automatically developed a set of novel prompts from several perspectives, including task-relevance, supportive evidence generation (e.g. chain-of-thought and knowledge), diverse path decoding to aid the model. Experimental results on ProtoQA dataset demonstrate that with better designed prompts we can achieve the new state-of-art(SOTA) on the ProtoQA leaderboard, improving the Max Answer@1 score by 8%, Max Incorrect@1 score by 4% (breakthrough 50% for the first time) compared to the previous SOTA model and achieved an improvement on StrategyQA and CommonsenseQA2.0 (3% and 1%, respectively). Furthermore, with the generated Chain-of-Thought and knowledge, we can improve the interpretability of the model while also surpassing the previous SOTA models. We hope that our work can provide insight for the NLP community to develop better prompts and explore the potential of large language models for more complex reasoning tasks.

arXiv:2308.04711

Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval

When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two methods for further improvement in this setting. Both methods focus on combining rationales generated by a larger Language Model with longer contexts created from a multi-hop dense retrieval system. The first method ($\textit{RR}$) involves training a Rationale Ranking model to score both generated rationales and retrieved contexts with respect to relevance and truthfulness. We then use the scores to derive combined contexts from both knowledge sources using a number of combinatory strategies. For the second method ($\textit{RATD}$) we utilise retrieval-augmented training datasets developed by Hartill et al. 2023 to train a smaller Reasoning model such that it becomes proficient at utilising relevant information from longer text sequences that may be only partially evidential and frequently contain many irrelevant sentences. We find that both methods significantly improve results. Our single best Reasoning model materially improves upon strong comparable prior baselines for unseen evaluation datasets (StrategyQA 58.9 $\rightarrow$ 61.7 acc., CommonsenseQA 63.6 $\rightarrow$ 72.7 acc., ARC-DA 31.6 $\rightarrow$ 52.1 F1, IIRC 25.5 $\rightarrow$ 27.3 F1) and a version utilising our prior knowledge of each type of question in selecting a context combination strategy does even better. Our proposed models also generally outperform direct prompts against much larger models (BLOOM 175B and StableVicuna 13B) in both few-shot chain-of-thought and standard few-shot settings.

arXiv:2308.00946공식 코드 · Papers with Code

Teaching Smaller Language Models To Generalise To Unseen Compositional Questions

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to instill diverse reasoning abilities, and a dense retrieval system that aims to retrieve a set of evidential paragraph fragments. Recent progress in question-answering has been achieved either through prompting methods against very large pretrained Language Models in zero or few-shot fashion, or by fine-tuning smaller models, sometimes in conjunction with information retrieval. We focus on the less explored question of the extent to which zero-shot generalisation can be enabled in smaller models with retrieval against a corpus within which sufficient information to answer a particular question may not exist. We establish strong baselines in this setting for diverse evaluation datasets (StrategyQA, CommonsenseQA, IIRC, DROP, Musique and ARC-DA), and show that performance can be significantly improved by adding retrieval-augmented training datasets which are designed to expose our models to a variety of heuristic reasoning strategies such as weighing partial evidence or ignoring an irrelevant context.

arXiv:2305.14507

Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models

We explore whether Large Language Models (LLMs) are capable of logical reasoning with distorted facts, which we call Deduction under Perturbed Evidence (DUPE). DUPE presents a unique challenge to LLMs since they typically rely on their parameters, which encode mostly accurate information, to reason and make inferences. However, in DUPE, LLMs must reason over manipulated or falsified evidence present in their prompts, which can result in false conclusions that are valid only under the manipulated evidence. Our goal with DUPE is to determine whether LLMs can arrive at these false conclusions and identify whether the dominant factor influencing the deduction process is the encoded data in the parameters or the manipulated evidence in the prompts. To evaluate the DUPE capabilities of LLMs, we create a DUPEd version of the StrategyQA dataset, where facts are manipulated to reverse the answer to the question. Our findings show that even the most advanced GPT models struggle to reason on manipulated facts - showcasing poor DUPE skills - with accuracy dropping by 45% compared to the original dataset. We also investigate prompt settings inspired from student simulation models, which mitigate the accuracy drop to some extent. Our findings have practical implications for understanding the performance of LLMs in real-world applications such as student simulation models that involve reasoning over inaccurate information.

arXiv:2305.11461

Hint of Thought prompting: an explainable and zero-shot approach to reasoning tasks with LLMs

Prompting becomes an increasingly important research topic for better utilization of LLMs. Although simple prompting performs well on single-step questions, it cannot permanently activate the correct knowledge path for multi-step reasoning tasks. The chain of thought (CoT), which often contains zero-shot CoT and few-shot CoT, is a recently developed prompting method that can explain the reasoning process to the LLM and outperforms simple prompting in three challenging reasoning tasks, including arithmetic, symbolic, and commonsense reasoning. Inspired by zero-shot CoT, and further extending the zero-shot ability, this paper proposes a novel hint of thought (HoT) prompting with explain-ability and zero-shot generalization. It is decomposed into three steps: explainable sub-questions, logical reasoning, and answering. Such three steps are sequentially ordered in step-by-step hints, which can be easily adjusted and explained to different tasks. Finally, experimental results demonstrate that our HoT prompting has a significant advantage on the zero-shot reasoning task compared to existing zero-shot CoT. We did zero-shot experiments on math tasks like GSM8K, ADDSUB, AQUA, SVAMP, and commonsense tasks such as StrategyQA. In particular, the accuracy of the proposed HoT prompting is improved with GSM8K from 40.50% to 70.65%, with AQUA from 31.9% to 46.4%, with SVAMP from 63.7% to 76.9%, and with ADDSUB from 74.7% to 87.34%, respectively, which even defeats the competitive PoT approach on GSM8k, AQUA, and SVAMP.

arXiv:2212.09656공식 코드 · Papers with Code

Visconde: Multi-document QA with GPT-3 and Neural Reranking

This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate. The first step decomposes the question into simpler questions using a few-shot large language model (LLM). Then, a state-of-the-art search engine is used to retrieve candidate passages from a large collection for each decomposed question. In the final step, we use the LLM in a few-shot setting to aggregate the contents of the passages into the final answer. The system is evaluated on three datasets: IIRC, Qasper, and StrategyQA. Results suggest that current retrievers are the main bottleneck and that readers are already performing at the human level as long as relevant passages are provided. The system is also shown to be more effective when the model is induced to give explanations before answering a question. Code is available at \url{https://github.com/neuralmind-ai/visconde}.

arXiv:2212.00193공식 코드 · Papers with Code

Distilling Reasoning Capabilities into Smaller Language Models

Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in inducing reasoning capabilities in large language models. However, the success of the CoT approach is fundamentally tied to the model size, and billion parameter-scale models are often needed to get CoT to work. In this paper, we propose a knowledge distillation approach that leverages the step-by-step CoT reasoning capabilities of larger models and distills these abilities into smaller models. In this work, we propose an alternative reasoning scheme, Socratic CoT, that learns a decomposition of the original problem into a sequence of subproblems and uses it to guide the intermediate reasoning steps. We use Socratic CoT to train a combination of two small distilled models: a problem decomposer and a subproblem solver. In practice, given a new problem, the two distilled models work in sync to decompose and solve complex problems. On multiple reasoning datasets (GSM8K, StrategyQA, and SVAMP), our proposed distillation strategies boosts the performance of smaller models over 70% compared to the baselines. Finally, we investigate when Socratic CoT is an effective alternative to CoT, demonstrating cases where a much smaller model (GPT-2 large) can outperform a 10X larger model (GPT-3 6B). Our code is available here: https://github.com/kumar-shridhar/Distiiling-LM

arXiv:2210.16865

Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite the many datasets and resources built as part of this effort, the majority have small-scale annotations and limited scope, which is insufficient to solve general decomposition tasks. In this paper, we look at large-scale intermediate pre-training of decomposition-based transformers using distant supervision from comparable texts, particularly large-scale parallel news. We show that with such intermediate pre-training, developing robust decomposition-based models for a diverse range of tasks becomes more feasible. For example, on semantic parsing, our model, DecompT5, improves 20% to 30% on two datasets, Overnight and TORQUE, over the baseline language model. We further use DecompT5 to build a novel decomposition-based QA system named DecompEntail, improving over state-of-the-art models, including GPT-3, on both HotpotQA and StrategyQA by 8% and 4%, respectively.

arXiv:2205.03685

Better Retrieval May Not Lead to Better Question Answering

Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC). A popular approach to improve the system's performance is to improve the quality of the retrieved context from the IR stage. In this work we show that for StrategyQA, a challenging open-domain QA dataset that requires multi-hop reasoning, this common approach is surprisingly ineffective -- improving the quality of the retrieved context hardly improves the system's performance. We further analyze the system's behavior to identify potential reasons.

arXiv:2204.02311

PaLM: Scaling Language Modeling with Pathways

Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of task-specific training examples needed to adapt the model to a particular application. To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model PaLM. We trained PaLM on 6144 TPU v4 chips using Pathways, a new ML system which enables highly efficient training across multiple TPU Pods. We demonstrate continued benefits of scaling by achieving state-of-the-art few-shot learning results on hundreds of language understanding and generation benchmarks. On a number of these tasks, PaLM 540B achieves breakthrough performance, outperforming the finetuned state-of-the-art on a suite of multi-step reasoning tasks, and outperforming average human performance on the recently released BIG-bench benchmark. A significant number of BIG-bench tasks showed discontinuous improvements from model scale, meaning that performance steeply increased as we scaled to our largest model. PaLM also has strong capabilities in multilingual tasks and source code generation, which we demonstrate on a wide array of benchmarks. We additionally provide a comprehensive analysis on bias and toxicity, and study the extent of training data memorization with respect to model scale. Finally, we discuss the ethical considerations related to large language models and discuss potential mitigation strategies.

arXiv:2203.15556

Training Compute-Optimal Large Language Models

We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. We find that current large language models are significantly undertrained, a consequence of the recent focus on scaling language models whilst keeping the amount of training data constant. By training over \nummodels language models ranging from 70 million to over 16 billion parameters on 5 to 500 billion tokens, we find that for compute-optimal training, the model size and the number of training tokens should be scaled equally: for every doubling of model size the number of training tokens should also be doubled. We test this hypothesis by training a predicted compute-optimal model, \chinchilla, that uses the same compute budget as \gopher but with 70B parameters and 4$\times$ more more data. \chinchilla uniformly and significantly outperforms \Gopher (280B), GPT-3 (175B), Jurassic-1 (178B), and Megatron-Turing NLG (530B) on a large range of downstream evaluation tasks. This also means that \chinchilla uses substantially less compute for fine-tuning and inference, greatly facilitating downstream usage. As a highlight, \chinchilla reaches a state-of-the-art average accuracy of 67.5\% on the MMLU benchmark, greater than a 7\% improvement over \gopher.

arXiv:2203.11171cs.CL

Self-Consistency Improves Chain of Thought Reasoning in Language Models

체인 오브 사고 프롬프트는 대형 언어 모델의 복잡한 추론 작업에서 성능을 향상시키는 데 중요한 역할을 하고 있다. 그러나 기존의 탐욕적 디코딩 전략은 종종 최적의 결과를 도출하지 못하는 한계를 지니고 있다. 이러한 문제를 해결하기 위해, 본 연구에서는 자기 일관성(self-consistency)이라는 새로운 디코딩 전략을 제안한다. 이 방법은 단순히 하나의 경로만을 선택하는 대신, 다양한 추론 경로를 샘플링하여 가장 일관된 답변을 선택하는 방식으로 진행된다. 이는 복잡한 문제에 대한 다양한 사고 방식을 반영하여, 언어 모델이 보다 정확한 결과를 도출할 수 있도록 돕는다. 자기 일관성 방법론은 여러 가지 추론 경로를 통해 생성된 후보 출력의 확률을 기반으로 답변을 집계함으로써, 정답의 일관성을 높인다. 본 연구의 실험 결과는 GSM8K, SVAMP, AQuA, StrategyQA, ARC-challenge와 같은 여러 벤치마크에서 자기 일관성이 체인 오브 사고 프롬프트의 성능을 유의미하게 향상시킨다는 것을 보여준다. 특히, 모델의 규모가 커질수록 성능 향상이 두드러지며, 이는 자기 일관성이 다양한 추론 작업에 효과적으로 적용될 수 있음을 시사한다. 결론적으로, 자기 일관성은 언어 모델의 추론 능력을 강화하는 혁신적인 접근 방식으로, 복잡한 문제 해결에 있어 보다 효과적인 방법을 제공한다. 이러한 연구는 언어 모델의 성능 향상뿐만 아니라, 향후 연구에서의 다양한 적용 가능성을 열어주는 중요한 기여로 평가될 수 있다.

arXiv:2112.11446

Scaling Language Models: Methods, Analysis & Insights from Training Gopher

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.

arXiv:2101.02235공식 코드 · Papers with Code

Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. A fundamental challenge in this setup is how to elicit such creative questions from crowdsourcing workers, while covering a broad range of potential strategies. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Moreover, we annotate each question with (1) a decomposition into reasoning steps for answering it, and (2) Wikipedia paragraphs that contain the answers to each step. Overall, StrategyQA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Analysis shows that questions in StrategyQA are short, topic-diverse, and cover a wide range of strategies. Empirically, we show that humans perform well (87%) on this task, while our best baseline reaches an accuracy of $\sim$66%.