We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide the reasoning steps, LLMs significantly improve their abilities in following a correct reasoning path towards the solution. We conduct experiments of Step-Back Prompting with PaLM-2L models and observe substantial performance gains on a wide range of challenging reasoning-intensive tasks including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back Prompting improves PaLM-2L performance on MMLU Physics and Chemistry by 7% and 11%, TimeQA by 27%, and MuSiQue by 7%.
"Thinking is for Doing." Humans can infer other people's mental states from observations--an ability called Theory-of-Mind (ToM)--and subsequently act pragmatically on those inferences. Existing question answering benchmarks such as ToMi ask models questions to make inferences about beliefs of characters in a story, but do not test whether models can then use these inferences to guide their actions. We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenarios. Experiments on T4D demonstrate that LLMs such as GPT-4 and PaLM 2 seemingly excel at tracking characters' beliefs in stories, but they struggle to translate this capability into strategic action. Our analysis reveals the core challenge for LLMs lies in identifying the implicit inferences about mental states without being explicitly asked about as in ToMi, that lead to choosing the correct action in T4D. To bridge this gap, we introduce a zero-shot prompting framework, Foresee and Reflect (FaR), which provides a reasoning structure that encourages LLMs to anticipate future challenges and reason about potential actions. FaR boosts GPT-4's performance from 50% to 71% on T4D, outperforming other prompting methods such as Chain-of-Thought and Self-Ask. Moreover, FaR generalizes to diverse out-of-distribution story structures and scenarios that also require ToM inferences to choose an action, consistently outperforming other methods including few-shot in-context learning.
Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications. Nevertheless, concerns persist regarding the accuracy and appropriateness of their generated content. A contemporary methodology, self-correction, has been proposed as a remedy to these issues. Building upon this premise, this paper critically examines the role and efficacy of self-correction within LLMs, shedding light on its true potential and limitations. Central to our investigation is the notion of intrinsic self-correction, whereby an LLM attempts to correct its initial responses based solely on its inherent capabilities, without the crutch of external feedback. In the context of reasoning, our research indicates that LLMs struggle to self-correct their responses without external feedback, and at times, their performance might even degrade post self-correction. Drawing from these insights, we offer suggestions for future research and practical applications in this field.
Language models still struggle on moral reasoning, despite their impressive performance in many other tasks. In particular, the Moral Scenarios task in MMLU (Multi-task Language Understanding) is among the worst performing tasks for many language models, including GPT-3. In this work, we propose a new prompting framework, Thought Experiments, to teach language models to do better moral reasoning using counterfactuals. Experiment results show that our framework elicits counterfactual questions and answers from the model, which in turn helps improve the accuracy on Moral Scenarios task by 9-16% compared to other zero-shot baselines. Interestingly, unlike math reasoning tasks, zero-shot Chain-of-Thought (CoT) reasoning doesn't work out of the box, and even reduces accuracy by around 4% compared to direct zero-shot. We further observed that with minimal human supervision in the form of 5 few-shot examples, the accuracy of the task can be improved to as much as 80%.
In this paper, we present InstructABSA, Aspect-Based Sentiment Analysis (ABSA) using instruction learning paradigm for all ABSA subtasks: Aspect Term Extraction (ATE), Aspect Term Sentiment Classification (ATSC), and Joint Task modeling. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tunes the model (Tk-Instruct Base) for each ABSA subtask, yielding significant performance improvements. Experimental results on the Sem Eval 2014 dataset demonstrate that InstructABSA outperforms the previous state-of-the-art (SOTA) approaches on all three ABSA subtasks (ATE, ATSC, and Joint Task) by a significant margin, outperforming 7x larger models. In particular, InstructABSA surpasses the SOTA on the restaurant ATE subtask by 7.31% points and on the Laptop Joint Task by 8.63% points. Our results also suggest a strong generalization ability to unseen tasks across all three subtasks.
Recent research has shown that language models exploit `artifacts' in benchmarks to solve tasks, rather than truly learning them, leading to inflated model performance. In pursuit of creating better benchmarks, we propose VAIDA, a novel benchmark creation paradigm for NLP, that focuses on guiding crowdworkers, an under-explored facet of addressing benchmark idiosyncrasies. VAIDA facilitates sample correction by providing realtime visual feedback and recommendations to improve sample quality. Our approach is domain, model, task, and metric agnostic, and constitutes a paradigm shift for robust, validated, and dynamic benchmark creation via human-and-metric-in-the-loop workflows. We evaluate via expert review and a user study with NASA TLX. We find that VAIDA decreases effort, frustration, mental, and temporal demands of crowdworkers and analysts, simultaneously increasing the performance of both user groups with a 45.8% decrease in the level of artifacts in created samples. As a by product of our user study, we observe that created samples are adversarial across models, leading to decreases of 31.3% (BERT), 22.5% (RoBERTa), 14.98% (GPT-3 fewshot) in performance.
Large "instruction-tuned" language models (finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is limited in quantity, diversity, and creativity, therefore hindering the generality of the tuned model. We introduce Self-Instruct, a framework for improving the instruction-following capabilities of pretrained language models by bootstrapping off its own generations. Our pipeline generates instruction, input, and output samples from a language model, then prunes them before using them to finetune the original model. Applying our method to vanilla GPT3, we demonstrate a 33% absolute improvement over the original model on Super-NaturalInstructions, on par with the performance of InstructGPT_001, which is trained with private user data and human annotations. For further evaluation, we curate a set of expert-written instructions for novel tasks, and show through human evaluation that tuning GPT3 with Self-Instruct outperforms using existing public instruction datasets by a large margin, leaving only a 5% absolute gap behind InstructGPT_001. Self-Instruct provides an almost annotation-free method for aligning pre-trained language models with instructions, and we release our large synthetic dataset to facilitate future studies on instruction tuning.
Mathematical reasoning skills are essential for general-purpose intelligent systems to perform tasks from grocery shopping to climate modeling. Towards evaluating and improving AI systems in this domain, we propose LILA, a unified mathematical reasoning benchmark consisting of 23 diverse tasks along four dimensions: (i) mathematical abilities e.g., arithmetic, calculus (ii) language format e.g., question-answering, fill-in-the-blanks (iii) language diversity e.g., no language, simple language (iv) external knowledge e.g., commonsense, physics. We construct our benchmark by extending 20 datasets benchmark by collecting task instructions and solutions in the form of Python programs, thereby obtaining explainable solutions in addition to the correct answer. We additionally introduce two evaluation datasets to measure out-of-distribution performance and robustness to language perturbation. Finally, we introduce BHASKARA, a general-purpose mathematical reasoning model trained on LILA. Importantly, we find that multi-tasking leads to significant improvements (average relative improvement of 21.83% F1 score vs. single-task models), while the best performing model only obtains 60.40%, indicating the room for improvement in general mathematical reasoning and understanding.
Pretrained Transformers (PT) have been shown to improve Out of Distribution (OOD) robustness than traditional models such as Bag of Words (BOW), LSTMs, Convolutional Neural Networks (CNN) powered by Word2Vec and Glove embeddings. How does the robustness comparison hold in a real world setting where some part of the dataset can be noisy? Do PT also provide more robust representation than traditional models on exposure to noisy data? We perform a comparative study on 10 models and find an empirical evidence that PT provide less robust representation than traditional models on exposure to noisy data. We investigate further and augment PT with an adversarial filtering (AF) mechanism that has been shown to improve OOD generalization. However, increase in generalization does not necessarily increase robustness, as we find that noisy data fools the AF method powered by PT.