Thailand

Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as &quot;Counseling Teacher&quot; to enhance smaller models&#39; emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies to ensure its quality and comprehensiveness. Based on this, we then devise a Diverse Response Inpainting (DRI) mechanism to harness the teacher model to produce multiple diverse responses by filling in the masked conversation context. This richness and variety serve as instructive examples, providing a robust foundation for fine-tuning smaller student models. Experiments across varied scenarios reveal that the teacher-student scheme with DRI notably improves the response abilities of smaller models, even outperforming the teacher model in some cases. The dataset and codes are available in https://github.com/pandazzh2020/ExTES.

ACL 2024

Self-chats from Large Language Models Make Small Emotional Support Chatbot Better

emotional support dialog

large language model

dialog dataset

Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as "Counseling Teacher" to enhance smaller models' emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies to ensure its quality and comprehensiveness. Based on this, we then devise a Diverse Response Inpainting (DRI) mechanism to harness the teacher model to produce multiple diverse responses by filling in the masked conversation context. This richness and variety serve as instructive examples, providing a robust foundation for fine-tuning smaller student models. Experiments across varied scenarios reveal that the teacher-student scheme with DRI notably improves the response abilities of smaller models, even outperforming the teacher model in some cases. The dataset and codes are available in https://github.com/pandazzh2020/ExTES.

poster

### 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. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **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!

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.

This work studies two types of ambiguity in natural language: prepositional phrase (PP) attachment ambiguity, and garden path constructions. Due to the different nature of these ambiguities -- one being structural, the other incremental in nature -- we pretrain and evaluate the Tree Transformer of Wang et al. (2019), an unsupervised Transformer model that induces tree representations internally. 
To assess PP attachment ambiguity we inspect the model's induced parse trees against a newly prepared dataset derived from the PP attachment corpus (Ratnaparkhi et al., 1994). Measuring garden path effects is done by considering surprisal rates of the underlying language model on a number of dedicated test suites, following Futrell et al. (2019). For comparison we evaluate a pretrained supervised BiLSTM-based model trained on constituency parsing as sequence labelling (Gómez-Rodríguez and Vilares, 2018). Results show that the unsupervised Tree Transformer does exhibit garden path effects, but its parsing ability is far inferior to the supervised BiLSTM, and it is not as sensitive to lexical cues as other large LSTM models, suggesting that supervised parsers based on a pre-Transformer architecture may be the better choice in the presence of ambiguity.

Tree Transformer’s Disambiguation Ability of Prepositional Phrase Attachment and Garden Path Effects

Journalists regularly make decisions on whether or not to report stories, based on "news values". In this work, we wish to explicitly model these decisions to explore _when_ and _why_ certain stories get press attention. This is challenging because very few labelled links between source documents and news articles exist and language use between corpora is very different. We address this problem by implementing a novel _probabilistic relational modeling_ framework, which we show is a low-annotation linking methodology that outperforms other, more state-of-the-art retrieval-based baselines. Next, we define a new task: __newsworthiness prediction__, to predict if a policy item will get covered. We focus on news coverage of local public policy in the San Francisco Bay Area by the _San Francisco Chronicle_. We gather 15k policies discussed across 10 years of public policy meetings, and transcribe over 3,200 hours of public discussion. In general, we find limited impact of public discussion on newsworthiness prediction accuracy, suggesting that some of the most important stories barely get discussed in public.
Finally, we show that newsworthiness predictions can be a useful assistive tool for journalists seeking to keep abreast of local government. We perform human evaluation with expert journalists and show our systems identify policies they consider newsworthy with 68\% F1 and our coverage recommendations are helpful with an 84\% win-rate against baseline. We release all code and data to our work here: https://github.com/alex2awesome/newsworthiness-public.

Tracking the Newsworthiness of Public Documents

Medical decisions directly impact individuals’ health and well-being. Extracting decision spans from clinical notes plays a crucial role in understanding medical decision-making processes. In this paper, we develop a new dataset called “MedDec,” which contains clinical notes of eleven different phenotypes (diseases) annotated by ten types of medical decisions. We introduce the task of medical decision extraction, aiming to jointly extract and classify different types of medical decisions within clinical notes. We provide a comprehensive analysis of the dataset, develop a span detection model as a baseline for this task, evaluate recent span detection approaches, and employ a few metrics to measure the complexity of data samples. Our findings shed light on the complexities inherent in clinical decision extraction and enable future work in this area of research. The dataset and code are available through https://github.com/CLU-UML/MedDec.

MedDec: A Dataset for Extracting Medical Decisions from Discharge Summaries

This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet under-examined capability for their application as AI agents. Despite LLMs' advancements, existing benchmarks fail to assess their format-following proficiency adequately. FoFo fills this gap with a diverse range of real-world formats and instructions, developed through an AI-Human collaborative method. Our evaluation across both open-source (e.g., Llama 2, WizardLM) and closed-source (e.g., GPT-4, PALM2, Gemini) LLMs highlights three key findings: open-source models significantly lag behind closed-source ones in format adherence; LLMs' format-following performance is independent of their content generation quality; and LLMs' format proficiency varies across different domains. These insights suggest the need for specialized tuning for format-following skills and highlight FoFo's role in guiding the selection of domain-specific AI agents. FoFo will be publicly released, contributing a critical tool for advancing LLM evaluation and application.

FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability

Large language models~(LLMs) have demonstrated striking reasoning capability. Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While humans can indeed imitate correct examples, learning from our mistakes is another vital aspect of human cognition. Hence, a question naturally arises: \textit{can LLMs learn and benefit from their mistakes, especially for their reasoning? }This study investigates this problem from both the prompting and model-tuning perspectives. We begin by introducing \textsc{CoTErrorSet}, a new benchmark with 609,432 questions, each designed with both correct and error references, and demonstrating the types and reasons for making such mistakes. To explore the effectiveness of those mistakes, we design two methods: (1) \textbf{Self-rethinking} prompting guides LLMs to rethink whether they have made similar previous mistakes; and (2) \textbf{Mistake tuning} involves finetuning models in both correct and incorrect reasoning domains, rather than only tuning models to learn ground truth in traditional methodology. We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions. Our two methods offer potentially cost-effective strategies by leveraging errors to enhance reasoning capabilities, which costs significantly less than creating meticulously hand-crafted golden references. We ultimately make a thorough analysis of the reasons behind LLMs' errors, which provides directions that future research needs to overcome. \textsc{CoTErrorSet} will be published soon on \texttt{\url{https://github.com/YookiTong/Learn-from-Mistakes-CotErrorSet}}.

Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning

Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments. However, the evaluation of these models has often been performed in a scattered way on only one or two specific tasks, in a few languages, at a partial granularity (e.g., function) level, and in many cases without proper training data. Even more concerning is that in most cases the evaluation of generated codes has been done in terms of mere lexical overlap with a reference code rather than actual execution. We introduce *xCodeEval*, the largest executable multilingual multitask benchmark to date consisting of $25$ M document-level coding examples ($16.5$ B tokens) from about $7.5$ K unique problems covering up to 11 programming languages with execution-level parallelism. It features a total of $7$ tasks involving code understanding, generation, translation and retrieval. *xCodeEval* adopts an execution-based evaluation and offers a multilingual code execution engine, *ExecEval* that supports unit test based execution in all the $11$ languages. To address the challenge of balancing the distributions of text-code samples over multiple attributes in validation/test sets, we propose a novel data splitting and a data selection schema based on the geometric mean and graph-theoretic principle. Our experiments with OpenAI's LLMs (zero-shot) and open-LLMs (zero-shot and fine-tuned) on the tasks and languages demonstrate to be quite challenging as per the current advancements in language models.

XCodeEval: An Execution-based Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval

We introduce the task of automatically revising scientific papers based on peer feedback and release ARIES, a dataset of review comments and their corresponding paper edits. The data is drawn from real reviewer-author interactions from computer science, and we provide labels linking each reviewer comment to the specific paper edits made by the author in response. We automatically create a high-precision silver training set, as well as an expert-labeled test set that shows high inter-annotator agreement. In experiments with 10 models covering the state of the art, we find that they struggle even to identify which edits correspond to a comment—especially when the relationship between the edit and the comment is indirect and requires reasoning to uncover. We also extensively analyze GPT-4’s ability to generate edits given a comment and the original paper. We find that it often succeeds on a superficial level, but tends to rigidly follow the wording of the feedback rather than the underlying intent, and lacks technical details compared to human-written edits.

ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews

Large Language Models (LLMs) have become integral components in various autonomous agent systems.
In this study, we present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to enhance the performance of open LLM agents. Contrary to previous studies that exclusively train on successful expert trajectories, our method allows agents to learn from their exploration failures. This leads to improved performance through an iterative optimization framework. During the exploration phase, the agent interacts with the environment while completing given tasks, gathering failure trajectories to create contrastive trajectory pairs. In the subsequent training phase, the agent utilizes these trajectory preference pairs to update its policy using contrastive learning methods like DPO. This iterative cycle of exploration and training fosters continued improvement in the agents. Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin. Furthermore, an examination of task-solving efficiency and potential in scenarios lacking expert trajectory underscores the effectiveness of our approach.

Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents

Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce ConstitutionalExperts, a method for learning a prompt consisting of constitutional principles (i.e. rules), given a training dataset. Unlike prior methods that optimize the prompt as a single entity, our method incrementally improves the prompt by surgically editing individual principles. We also show that we can improve overall performance by learning unique prompts for different semantic regions of the training data and using a mixture-of-experts (MoE) architecture to route inputs at inference time. We compare our method to other state of the art prompt-optimization techniques across six benchmark datasets. We also investigate whether MoE improves these other techniques. Our results suggest that ConstitutionalExperts outperforms other prompt optimization techniques by 10.9% (F1) and that mixture-of-experts improves all techniques, suggesting its broad applicability.

ConstitutionalExperts: Training a Mixture of Principle-based Prompts

Benchmarks have emerged as the central approach for evaluating Large Language Models (LLMs). The research community often relies on a model’s average performance across the test prompts of a benchmark to evaluate the model’s performance. This is consistent with the assumption that the test prompts within a benchmark represent a random sample from some real-world distribution of interest. We note that this is generally not the case; instead, we hold that the distribution of interest varies according to the specific use case. Hence, we analyze the robustness of LLM benchmarks to their underlying distributional assumptions. We find that (1) the correlation in model performance across test prompts is non-random, (2) accounting for correlations across test prompts can change model rankings on major benchmarks, (3) explanatory factors for these correlations include semantic similarity and common LLM failure points.

Premium content

Self-chats from Large Language Models Make Small Emotional Support Chatbot Better

Downloads

Next from ACL 2024

Tree Transformer’s Disambiguation Ability of Prepositional Phrase Attachment and Garden Path Effects

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES