Canada

Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series of reasoning steps in the demonstrations. Despite its success, there is still little understanding of what makes CoT prompting effective and which aspects of the demonstrated reasoning steps contribute to its performance. In this paper, we show that CoT reasoning is possible even with invalid demonstrations - prompting with invalid reasoning steps can achieve over 80-90% of the performance obtained using CoT under various metrics, while still generating coherent lines of reasoning during inference. Further experiments show that other aspects of the rationales, such as being relevant to the query and correctly ordering the reasoning steps, are much more important for effective CoT reasoning. Overall, these findings both deepen our understanding of CoT prompting, and open up new questions regarding LLMs&#39; capability to learn to reason in context.

&lt;iframe src=&quot;https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/fc764a6f-6d74-4e55-8428-29d16cafcb0b&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters

chain-of-thought

large language models

reasoning

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. <br>Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.<br><br><br>

You are required to register for this event. <br>**Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.


Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series of reasoning steps in the demonstrations. Despite its success, there is still little understanding of what makes CoT prompting effective and which aspects of the demonstrated reasoning steps contribute to its performance. In this paper, we show that CoT reasoning is possible even with invalid demonstrations - prompting with invalid reasoning steps can achieve over 80-90% of the performance obtained using CoT under various metrics, while still generating coherent lines of reasoning during inference. Further experiments show that other aspects of the rationales, such as being relevant to the query and correctly ordering the reasoning steps, are much more important for effective CoT reasoning. Overall, these findings both deepen our understanding of CoT prompting, and open up new questions regarding LLMs' capability to learn to reason in context.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/fc764a6f-6d74-4e55-8428-29d16cafcb0b" width="300" height="400"></iframe>

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Unsupervised speech recognition (\asru/) is the problem of learning automatic speech recognition (ASR) systems from \emph{unpaired} speech-only and text-only corpora. While various algorithms exist to solve this problem, a theoretical framework is missing to study their properties and address such issues as sensitivity to hyperparameters and training instability. In this paper, we proposed a general theoretical framework to study the properties of \asru/ systems based on random matrix theory and the theory of neural tangent kernels. Such a framework allows us to prove various learnability conditions and sample complexity bounds of \asru/. Extensive \asru/ experiments on synthetic languages with three classes of transition graphs provide strong empirical evidence for our theory (code available at \href{https://github.com/cactuswiththoughts/UnsupASRTheory.git}{cactuswiththoughts/UnsupASRTheory.git}).

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/3ba37d75-57f4-4a5c-9be1-ce1e89985143" width="300" height="400"></iframe>

A Theory of Unsupervised Speech Recognition

\textit{\textbf{\textcolor{red}{Warning}:} This paper contains content that may be offensive or upsetting.}Pretrained conversational agents have been exposed to safety issues, exhibiting a range of stereotypical human biases such as gender bias. However, there are still limited bias categories in current research, and most of them only focus on English. In this paper, we introduce a new Chinese dataset, CHBias, for bias evaluation and mitigation of Chinese conversational language models.Apart from those previous well-explored bias categories, CHBias includes under-explored bias categories, such as ageism and appearance biases, which received less attention. We evaluate two popular pretrained Chinese conversational models, CDial-GPT and EVA2.0, using CHBias. Furthermore, to mitigate different biases, we apply several debiasing methods to the Chinese pretrained models. Experimental results show that these Chinese pretrained models are potentially risky for generating texts that contain social biases, and debiasing methods using the proposed dataset can make response generation less biased while preserving the models' conversational capabilities.

<iframe src="https://app.sli.do/event/nDU9hzdsVZXUCPdEbR3oSF/embed/polls/d930fa48-c955-440d-980d-e5d9882c4999" width="300" height="400"></iframe>

CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models

Human evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and its quality is notoriously unstable, hindering fair comparisons among different natural language processing (NLP) models and algorithms.Recently, large language models (LLMs) have demonstrated exceptional performance on unseen tasks when only the task instructions are provided.In this paper, we explore if such an ability of the LLMs can be used as an alternative to human evaluation.We present the LLMs with the exact same instructions, samples to be evaluated, and questions used to conduct human evaluation, and then ask the LLMs to generate responses to those questions; we dub this LLM evaluation.We use human evaluation and LLM evaluation to evaluate the texts in two NLP tasks: open-ended story generation and adversarial attacks.We show that the result of LLM evaluation is consistent with the results obtained by expert human evaluation: the texts rated higher by human experts are also rated higher by the LLMs.We also find that the results of LLM evaluation are stable over different formatting of the task instructions and the sampling algorithm used to generate the answer.We are the first to show the potential of using LLMs to assess the quality of texts and discuss the limitations and ethical considerations of LLM evaluation.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/795d41bd-f09a-4334-a489-ed7c2a3d0c7c" width="300" height="400"></iframe>

Can Large Language Models Be an Alternative to Human Evaluations?

Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes the gap by constructing pseudo-demonstrations for a given test input using a raw text corpus. Concretely, pseudo-demonstrations are constructed by (1) finding the nearest neighbors to the test input from the corpus and pairing them with random task labels, and (2) applying a set of techniques to reduce the amount of direct copying the model does from the resulting demonstrations. Evaluation on nine classification datasets shows that Z-ICL outperforms previous zero-shot methods by a significant margin, and is on par with in-context learning with labeled training data in the few-shot setting. Overall, Z-ICL provides a significantly higher estimate of the zero-shot performance levels of a model, and supports future efforts to develop better pseudo-demonstrations that further improve zero-shot results.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/ad3e8cef-03f2-4787-b98b-545b8fafdd8a" width="300" height="400"></iframe>

Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations

A key missing capacity of current language models (LMs) is grounding to real-world environments. Most existing work for grounded language understanding uses LMs to directly generate plans that can be executed in the environment to achieve the desired effects. It thereby casts the burden of ensuring grammaticality, faithfulness, and controllability all on the LMs. We propose Pangu, a generic framework for grounded language understanding that capitalizes on the discriminative ability of LMs instead of their generative ability. Pangu consists of a symbolic agent and a neural LM working in a concerted fashion: The agent explores the environment to incrementally construct valid plans, and the LM evaluates the plausibility of the candidate plans to guide the search process. A case study on the challenging problem of knowledge base question answering (KBQA), which features a massive environment, demonstrates the remarkable effectiveness and flexibility of Pangu: A BERT-base LM is sufficient for setting a new record on standard KBQA datasets, and larger LMs further bring substantial gains.Pangu also enables, for the first time, effective few-shot in-context learning for KBQA with large LMs such as Codex.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/f617f069-dc51-442a-8920-e54bab31c545" width="300" height="400"></iframe>

Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

Social media is one of the most highly sought resources for analyzing characteristics of the language by its users. In particular, many researchers utilized various linguistic features of mental health problems from social media. However, existing approaches to detecting mental disorders face critical challenges, such as the scarcity of high-quality data or the trade-off between addressing the complexity of models and presenting interpretable results grounded in expert domain knowledge. To address these challenges, we design a simple but flexible model that preserves domain-based interpretability. We propose a novel approach that captures the semantic meanings directly from the text and compares them to symptom-related descriptions. Experimental results demonstrate that our model outperforms relevant baselines on various mental disorder detection tasks. Our detailed analysis shows that the proposed model is effective at leveraging domain knowledge, transferable to other mental disorders, and providing interpretable detection results.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/770e8e82-4a27-4b0f-87ae-bb33406590ff" width="300" height="400"></iframe>

A Simple and Flexible Modeling for Mental Disorder Detection by Learning from Clinical Questionnaires

The recently released NLLB-200 is a set of multilingual Neural Machine Translation models that cover 202 languages. The largest model is based on a Mixture of Experts architecture and achieves SoTA results across many language pairs. It contains 54.5B parameters and requires at least four 32GB GPUs just for inference.In this work, we propose a pruning method that enables the removal of up to 80% of experts without further finetuning and with a negligible loss in translation quality, which makes it feasible to run the model on a single 32GB GPU. Further analysis suggests that our pruning metrics can identify language-specific experts.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/e75086cf-c6cd-4192-9075-9084daeee5b8" width="300" height="400"></iframe>

Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model

Languages differ in how they divide up the world into concepts and words; e.g., in contrast to English, Swahili has a single concept for 'belly' and 'womb'. We investigate these differences in conceptualization across 1,335 languages by aligning concepts in a parallel corpus. To this end, we propose Conceptualizer, a method that creates a bipartite directed alignment graph between source language concepts and sets of target language strings. In a detailed linguistic analysis across all languages for one concept ('bird') and an evaluation on gold standard data for 32 Swadesh concepts, we show that Conceptualizer has good alignment accuracy. We demonstrate the potential of research on conceptualization in NLP with two experiments. (1) We define crosslingual stability of a concept as the degree to which it has 1-1 correspondences across languages, and show that concreteness predicts stability. (2) We represent each language by its conceptualization pattern for 83 concepts, and define a similarity measure on these representations. The resulting measure for the conceptual similarity between two languages is complementary to standard genealogical, typological, and surface similarity measures. For four out of six language families, we can assign languages to their correct family based on conceptual similarity with accuracies between 54% and 87%

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/cea3315b-399d-4ac7-b030-0642da6d84dc" width="300" height="400"></iframe>

A Crosslingual Investigation of Conceptualization in 1335 Languages

Graph-based prediction is essential in NLP tasks such as temporal knowledge graph completion. A cardinal question in this field is, how to predict the future links, nodes, and attributes of a time-evolving attributed graph? Unfortunately, existing techniques assume that each link, node, and attribute prediction is independent, and fall short of predicting the appearance of new nodes that were not observed in the past. In this paper, we address two interrelated questions; (1) can we exploit task interdependence to improve prediction accuracy? and (2) can we predict new nodes with their attributes? We propose a unified framework that predicts node attributes and topology changes such as the appearance and disappearance of links and the emergence and loss of nodes. This frame-work comprises components for independent and interactive prediction and for predicting new nodes. Our experimental study using real-world data confirms that our interdependent prediction framework achieves higher accuracy than methods based on independent prediction.

<iframe src="https://app.sli.do/event/eX4PwSmcCc1EvCqjxcYdKB/embed/polls/c3159d64-b39b-4d13-aa4e-a9458b8bde3d" width="300" height="400"></iframe>

Holistic Prediction on a Time-Evolving Attributed Graph

Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative. In this work, we argue that due to the gradual improvement across model layers, additional information can be gleaned from the contrast between higher and lower layers during inference. Specifically, in choosing between the probable next token predictions of a generative model, the predictions of lower layers can be used to highlight which candidates are best avoided. We propose a novel approach that utilizes the contrast between layers to improve text generation outputs, and show that it mitigates degenerative behaviors of the model in open-ended generation, significantly improving the quality of generated texts. Furthermore, our results indicate that contrasting between model layers at inference time can yield substantial benefits to certain aspects of general language model capabilities, more effectively extracting knowledge during inference from a given set of model parameters.

<iframe src="https://app.sli.do/event/eX4PwSmcCc1EvCqjxcYdKB/embed/polls/00dff520-10d2-4195-be4a-21b512a61354" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

A Theory of Unsupervised Speech Recognition

Similar lecture

The Impact of Reasoning Step Length on Large Language Models