Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking

Generating free-text rationales is among the emergent capabilities of Large Language Models (LLMs). These rationales have been found to enhance LLM performance across various NLP tasks. Recently, there has been growing interest in using these rationales to provide insights for various important downstream tasks. In this paper, we analyze generated free-text rationales in tasks with subjective answers, emphasizing the importance of rationalization in such scenarios. We focus on pairwise argument ranking, a highly subjective task with significant potential for real-world applications, such as debate assistance. We evaluate the persuasiveness of rationales generated by nine LLMs to support their subjective choices. Our findings suggest that open-source LLMs, particularly Llama2-70B-chat, are capable of providing highly persuasive rationalizations, surpassing even GPT models. Additionally, our experiments show that rationale persuasiveness can be improved by controlling its parameters through prompting or through self-refinement.

Every Answer Matters: Evaluating Commonsense with Probabilistic Measures

Large language models have demonstrated impressive performance on commonsense tasks; however, these tasks are often posed as multiple-choice questions, allowing models to exploit systematic biases. Commonsense is also inherently probabilistic with multiple correct answers. The purpose of "boiling water" could be making tea and cooking, but it also could be killing germs. Existing tasks do not capture the probabilistic nature of common sense. To this end, we present commonsense frame completion (CFC), a new generative task that evaluates common sense via multiple open-ended generations. We also propose a method of probabilistic evaluation that strongly correlates with human judgments. Humans drastically outperform strong language model baselines on our dataset, indicating this approach is both a challenging and useful evaluation of machine common sense.

Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition

Existing object recognition models have been shown to lack robustness in diverse geographical scenarios due to significant domain shifts in design and context. Class representations need to be adapted to more accurately reflect an object concept under these shifts. In the absence of training data from target geographies, we hypothesize that geography-specific descriptive knowledge of object categories can be leveraged to enhance robustness. For this purpose, we explore the feasibility of probing a large-language model for geography-specific object knowledge, and we investigate integrating knowledge in zero-shot and learnable soft prompting with the CLIP vision-language model. In particular, we propose a geography knowledge regularization method to ensure that soft prompts trained on a source set of geographies generalize to an unseen target set of geographies. Our gains on DollarStreet when generalizing from a model trained only on data from Europe are as large as +2.8 on countries from Africa, and +4.6 on the hardest classes. We further show competitive performance vs. few-shot target training, and provide insights into how descriptive knowledge captures geographical differences.

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the ability to model unusual, unexpected, and unlikely situations, we explore the task of uncommonsense abductive reasoning. Given a piece of context with an unexpected outcome, this task requires reasoning abductively to generate a natural language explanation that makes the unexpected outcome more likely in the context. To this end, we curate and release a new English language corpus called UNcommonsense. We characterize the differences between the performance of human explainers and the best performing large language models, finding that model-enhanced human-written explanations achieve the highest quality by trading off between specificity and diversity. Finally, we experiment with several online imitation learning algorithms to train open and accessible language models on this task. When compared with the vanilla supervised fine-tuning approach, these methods consistently reduce lose rates on both common and uncommonsense abductive reasoning judged by human evaluators.

In Search of the Long-Tail: Systematic Generation of Long-Tail Knowledge via Logical Rule Guided Search

Since large language models have approached human-level performance on many tasks, it has become increasingly harder for researchers to find tasks that are still challenging to the models. Failure cases usually come from the long-tail distribution - data that an oracle language model could assign a probability on the lower end of its distribution. Current methodology such as prompt engineering or crowdsourcing are insufficient for creating long-tail examples because humans are constrained by cognitive bias. We propose a Logic-Induced-Knowledge-Search (LINK) framework for systematically generating long-tail knowledge statements. Grounded by a symbolic rule, we search for long-tail values for each variable of the rule by first prompting a LLM, then verifying the correctness of the values with a critic, and lastly pushing for the long-tail distribution with a reranker. With this framework we construct a dataset, Logic-Induced-Long-Tail (LINT), consisting of 200 symbolic rules and 50K knowledge statements spanning across four domains. Human annotations find that 84% of the statements in LINT are factually correct. In contrast, ChatGPT and GPT4 struggle with directly generating long-tail statements under the guidance of logic rules, each only getting 56% and 78% of their statements correct. Moreover, their "long-tail" generations in fact fall into the higher likelihood range, and thus are not really long-tail. Our findings suggest that LINK is effective for generating data in the long-tail distribution while enforcing quality. LINT can be useful for systematically evaluating LLMs' capabilities in the long-tail distribution. We challenge the models with a simple entailment classification task using samples from LINT. We find that ChatGPT and GPT4's capability in identifying incorrect knowledge drop by ~3% in the long-tail distribution compared to head distribution.

Faith and Fate: Limits of Transformers on Compositionality

Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems. This begs the question: Are these errors incidental, or do they signal more substantial limitations? In an attempt to demystify Transformers, we investigate the limits of these models across three representative compositional tasks -- multi-digit multiplication, logic grid puzzles, and a classic dynamic programming problem. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures. Our empirical findings suggest that Transformers solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching, without necessarily developing systematic problem-solving skills. To round off our empirical study, we provide theoretical arguments on abstract multi-step reasoning problems that highlight how Transformers' performance will rapidly decay with increased task complexity.

PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning

Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex contextualized situations that are often counterfactual, e.g. "scheduling a doctor's appointment without a phone". While current approaches show encouraging results using large language models (LLMs), they are hindered by drawbacks such as costly API calls and reproducibility issues. In this paper, we advocate planning using smaller language models. We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (counterfactual) planning capabilities. More concretely, we develop symbolic procedural knowledge distillation to enhance the implicit knowledge in small language models and an inference-time algorithm to facilitate more structured and accurate reasoning. In addition, we introduce a novel task, Counterfactual Planning, that requires a revision of a plan to cope with a counterfactual situation. In both the original and counterfactual setting, we show that orders-of-magnitude smaller models (770M-11B parameters) can compete and often surpass their larger teacher models' capabilities.

Editing Commonsense Knowledge in GPT

Memory editing methods for updating encyclopedic knowledge in transformers have received increasing attention for their efficacy, specificity, and generalization advantages. However, it remains unclear if such methods can be adapted for the more nuanced domain of commonsense knowledge. We propose $MEMIT_{CSK}$, an adaptation of MEMIT to edit commonsense mistakes in GPT-2 Large and XL. We extend editing to various token locations and employ a robust layer selection strategy. Models edited by $MEMIT_{CSK}$ outperforms the fine-tuning baselines by 10.97% and 10.73% F1 scores on subsets of PEP3k and 20Q. We further propose a novel evaluation dataset, MEMIT-CSK-PROBE, that contains unaffected neighborhood, affected neighborhood, affected paraphrase, and affected reasoning challenges. $MEMIT_{CSK}$ demonstrates favorable semantic generalization, outperforming fine-tuning baselines by 13.72% and 5.57% overall scores on MEMIT-CSK-PROBE. These results suggest a compelling future direction of incorporating context-specific user feedback concerning commonsense in GPT by direct model editing, rectifying and customizing model behaviors via human-in-the-loop systems.

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.

A Systematic Investigation of Commonsense Understanding in Large Language Models

Large language models have shown impressive performance on many natural language processing (NLP) tasks in a zero-shot setting. We ask whether these models exhibit commonsense understanding -- a critical component of NLP applications -- by evaluating models against four commonsense benchmarks. We find that the impressive zero-shot performance of large language models is mostly due to existence of dataset bias in our benchmarks. We also show that the zero-shot performance is sensitive to the choice of hyper-parameters and similarity of the benchmark to the pre-training datasets. Moreover, we did not observe substantial improvements when evaluating models in a few-shot setting. Finally, in contrast to previous work, we find that leveraging explicit commonsense knowledge does not yield substantial improvement.