Thailand

Planning in a text-based environment continues to be a significant challenge for AI systems. Recent approaches have utilized language models to predict planning domain definitions (e.g., PDDL) but have only been evaluated in closed-domain simulated environments. To address this, we present Proc2PDDL, the first dataset containing open-domain procedural texts paired with expert-annotated PDDL representations. Using this dataset, we evaluate the task of predicting domain actions (parameters, preconditions, and effects). We experiment with various large language models (LLMs) and prompting mechanisms, including a novel instruction inspired by the zone of proximal development (ZPD), which reconstructs the task as incremental basic skills. Our results demonstrate that Proc2PDDL is highly challenging for end-to-end LLMs, with GPT-3.5&#39;s success rate close to 0% and GPT-4o&#39;s 38%. With ZPD instructions, GPT-4o&#39;s success rate increases to 45%, outperforming regular chain-of-thought prompting&#39;s 34%. Our analysis systematically examines both syntactic and semantic errors, providing insights into the strengths and weaknesses of language models in generating domain-specific programs.

ACL 2024

PROC2PDDL: Open-Domain Planning Representations from Texts

planning

translation

reasoning

Planning in a text-based environment continues to be a significant challenge for AI systems. Recent approaches have utilized language models to predict planning domain definitions (e.g., PDDL) but have only been evaluated in closed-domain simulated environments. To address this, we present Proc2PDDL, the first dataset containing open-domain procedural texts paired with expert-annotated PDDL representations. Using this dataset, we evaluate the task of predicting domain actions (parameters, preconditions, and effects). We experiment with various large language models (LLMs) and prompting mechanisms, including a novel instruction inspired by the zone of proximal development (ZPD), which reconstructs the task as incremental basic skills. Our results demonstrate that Proc2PDDL is highly challenging for end-to-end LLMs, with GPT-3.5's success rate close to 0% and GPT-4o's 38%. With ZPD instructions, GPT-4o's success rate increases to 45%, outperforming regular chain-of-thought prompting's 34%. Our analysis systematically examines both syntactic and semantic errors, providing insights into the strengths and weaknesses of language models in generating domain-specific programs.

workshop paper

### 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.

Everlasting contact between language communities leads to constant changes in languages over time, and gives rise to language varieties and dialects. However, the communities speaking non-standard language are often overlooked by non-inclusive NLP technologies. Recently, there has been a surge of interest in studying diatopic and diachronic changes in dialect NLP, but there is currently no research exploring the intersection of both. Our work aims to fill this gap by systematically reviewing diachronic and diatopic papers from a unified perspective. In this work, we critically assess nine tasks and datasets across five dialects from three language families (Slavic, Romance, and Germanic) in both spoken and written modalities. The tasks covered are diverse, including corpus construction, dialect distance estimation, and dialect geolocation prediction, among others. Moreover, we outline five open challenges regarding changes in dialect use over time, the reliability of dialect datasets, the importance of speaker characteristics, limited coverage of dialects, and ethical considerations in data collection. We hope that our work sheds light on future research towards inclusive computational methods and datasets for language varieties and dialects.

Exploring Diachronic and Diatopic Changes in Dialect Continua: Tasks, Datasets and Challenges

This paper describes our contribution to Subtask 1 of the AXOLOTL-24 Shared Task on unsupervised lexical semantic change modeling. In a joint task of word sense disambiguation and word sense induction on diachronic corpora, we significantly outperform the baseline by merging clusters of modern usage examples based on their similarities with the same historical word sense as well as their mutual similarities. We observe that multilingual sentence embeddings outperform language-specific ones in this task.

Similarity-Based Cluster Merging for Semantic Change Modeling

This paper explores the evolution of word meanings in 19th-century Spanish texts, with an emphasis on Latin American Spanish, using computational linguistics techniques. It addresses the Semantic Shift Detection (SSD) task, which is crucial for understanding linguistic evolution, particularly in historical contexts. The study focuses on analyzing a set of Spanish target words. To achieve this, a 19th-century Spanish corpus is constructed, and a customizable pipeline for SSD tasks is developed. This pipeline helps find the senses of a word and measure their semantic change between two corpora using fine-tuned BERT-like models with old Spanish texts for both Latin American and general Spanish cases. The results provide valuable insights into the cultural and societal shifts reflected in language changes over time.

Historical Ink: Semantic Shift Detection for 19th Century Spanish

There has been a surge of interest in computational modeling of semantic change. The foci of previous works are on detecting and interpreting word senses gained over time; however, it remains unclear whether the gained senses are covered by dictionaries. In this work, we aim to fill this research gap by comparing detected word senses with dictionary sense inventories in order to bridge between the communities of lexical semantic change detection and lexicography. We evaluate our system in the AXOLOTL-24 shared task for Finnish, Russian and German languages \cite{fedorova-etal-2024-axolotl}. Our system is fully unsupervised. It leverages a graph-based clustering approach to predict mappings between unknown word usages and dictionary entries for Subtask 1, and generates dictionary-like definitions for those novel word usages through the state-of-the-art Large Language Models such as GPT-4 and LLaMA-3 for Subtask 2. In Subtask 1, our system outperforms the baseline system by a large margin, and it offers interpretability for the mapping results by distinguishing between matched and unmatched (novel) word usages through our graph-based clustering approach. Our system ranks first in Finnish and German, and ranks second in Russian on the Subtask 2 test-phase leaderboard. These results show the potential of our system in managing dictionary entries, particularly for updating dictionaries to include novel sense entries. Our code and data are made publicly available at https://github.com/xiaohemaikoo/axolotl24-ABDN-NLP.

Presence or Absence: Are Unknown Word Usages in Dictionaries?

This paper is concerned with annotating the syntax of ancient Chinese, which is a series of languages in the same development process. The major challenge is to ensure the annotations of languages at different stages are comparable. To this end, we propose a feature-based approach that integrates the deductive feature design from the Chomskyan school and the inductive feature design from traditional philological studies. We demonstrate the effectiveness of our approach by annotating a collection of representative sentences that cover various linguistic phenomena that are extensively discussed in the literature. As a result, we establish a corpus of 673 (for now) ancient Chinese sentences paired with syntactic analyses, covering from 700s B.C.E. to 1900s C.E. The corpus can be utilised as a guideline for future large-scale TreeBanking.

A Feature-Based Approach to Annotate the Syntax of Ancient Chinese

Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities. We generally divide multi-step reasoning into two phases: *path generation* to generate the reasoning path(s); and *answer calibration* post-processing the reasoning path(s) to obtain a final answer. However, the existing literature lacks systematic analysis on different answer calibration approaches. In this paper, we summarize the taxonomy of recent answer calibration techniques and break them down into step-level and path-level strategies. We then conduct a thorough evaluation on these strategies from a unified view, systematically scrutinizing step-level and path-level answer calibration across multiple paths. Experimental results reveal that integrating the dominance of both strategies tends to derive optimal outcomes. Our study holds the potential to illuminate key insights for optimizing multi-step reasoning with answer calibration.

Towards A Unified View of Answer Calibration for Multi-Step Reasoning

Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), most studies have failed to rigorously differentiate between inductive and deductive reasoning, leading to a blending of the two. This raises an essential question: In LLM reasoning, which poses a greater challenge - deductive or inductive reasoning? While the deductive reasoning capabilities of LLMs, (i.e. their capacity to follow instructions in reasoning tasks), have received considerable attention, their abilities in true inductive reasoning remain largely unexplored. To delve into the true inductive reasoning capabilities of LLMs, we propose a novel framework, SolverLearner. This framework enables LLMs to learn the underlying function (i.e., $y = f_w(x)$), that maps input data points $(x)$ to their corresponding output values $(y)$, using only in-context examples. By focusing on inductive reasoning and separating it from LLM-based deductive reasoning, we can isolate and investigate inductive reasoning of LLMs in its pure form via SolverLearner. Our observations reveal that LLMs demonstrate remarkable inductive reasoning capabilities through SolverLearner, achieving near-perfect performance with ACC of 1 in most cases. Surprisingly, despite their strong inductive reasoning abilities, LLMs tend to relatively lack deductive reasoning capabilities, particularly in tasks involving ``counterfactual'' reasoning.

Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs

Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains, including mitigating harm in LLM outputs, enhancing text summarization, and mathematical reasoning. This paper introduces an RLAIF framework for improving the code generation abilities of lightweight (<1B parameters) LLMs. We specifically focus on code generation tasks that require writing appropriate API calls, which is challenging due to the well-known issue of hallucination in LLMs. Our framework extracts AI feedback from a larger LLM (e.g., GPT-3.5) through a specialized prompting strategy and uses this data to train a reward model towards better alignment from smaller LLMs. We run our experiments on the Gorilla dataset and meticulously assess the quality of the model-generated code across various metrics, including AST, ROUGE, and Code-BLEU, and develop a pipeline to compute its executability rate accurately. Our approach significantly enhances the fine-tuned LLM baseline's performance, achieving a 4.5\% improvement in executability rate. Notably, a smaller LLM model (780M parameters) trained with RLAIF surpasses a much larger fine-tuned baseline with 7B parameters, achieving a 1.0\% higher code executability rate.

Applying RLAIF for Code Generation with API-usage in Lightweight LLMs

Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary models is costly and not scalable. In this paper, we study the problem of whether LLMs could self-improve their reasoning capabilities. To this end, we propose Self-Explore, where the LLM is tasked to explore the first wrong step (i.e., the first pit) within the rationale and use such signals as fine-grained rewards for further improvement. On the GSM8K and MATH test set, Self-Explore achieves 11.57% and 2.89% improvement on average across three LLMs compared to supervised fine-tuning (SFT). Our code is available at https://anonymous.4open.science/r/Self_Explore-220B.

Self-Explore to Avoid the Pit: Improving the Reasoning Capabilities of Language Models with Fine-grained Rewards

While forward reasoning (i.e., find the answer given the question) has been explored extensively in recent literature, backward reasoning is relatively unexplored. We examine the backward reasoning capabilities of LLMs on Math Word Problems (MWPs): given a mathematical question and its answer, with some details omitted from the question, can LLMs effectively retrieve the missing information? On modifying three benchmark datasets for this task, to evaluate this task: GSM8k, SVAMP, and MultiArith, we find a significant drop in the accuracy of models on this task compared to forward reasoning across SOTA LLMs (GPT4, GPT3.5, PaLM-2, and LLaMa). Motivated by the fact backward reasoning can be seen as the ``inverse'' of forward reasoning, we propose variations of three different forward reasoning strategies to improve performance. Rephrase reformulates the given problem into a forward reasoning problem, PAL-Tools combines the idea of Program-Aided LLMs to produce a set of equations that can be solved by an external solver, and Check your Work exploits the availability of natural verifier of high accuracy in the forward direction, interleaving solving and verification steps. Finally, realizing that each of our base methods correctly solves a different set of problems, we propose a novel Bayesian formulation for creating an ensemble over the base methods to further boost the accuracy. Extensive experimentation demonstrates successive improvement in the performance of LLMs on the backward reasoning task, using our strategies, with our ensemble-based method resulting in significant performance gains compared to the SOTA forward reasoning strategies we adapt.

Premium content

PROC2PDDL: Open-Domain Planning Representations from Texts

Downloads

Next from ACL 2024

Exploring Diachronic and Diatopic Changes in Dialect Continua: Tasks, Datasets and Challenges

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES