Thailand

The evolution of large language models (LLMs) has culminated in a multitask model paradigm where prompts drive the generation of user-specific outputs. However, this advancement has revealed a critical challenge: LLMs frequently produce outputs against socially acceptable commonsense standards in various scenarios. To address this gap in commonsense reasoning, we present KoCommonGEN v2, a fine-grained benchmark dataset focused on Korean commonsense reasoning. This dataset, enriched with human annotations, comprises multiple-choice questions across seven error categories. These categories include commonsense memorization, numerical commonsense, toxic speech, and more, which are vulnerable to undermining the reliability of LLMs&#39; commonsense reasoning capabilities. The empirical results present that LLMs struggle with Korean commonsense reasoning. With human accuracy benchmarked at approximately 85%, GPT-4&#39;s performance lags at about 74%, and other LLMs demonstrate an average accuracy of around 42%. Our findings emphasize the need for targeted improvements in Korean commonsense reasoning within LLMs, paving the way for more socially and contextually sensitive AI models.

ACL 2024

KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models

socio-cultural commonsense reasoning

korean

benchmark

The evolution of large language models (LLMs) has culminated in a multitask model paradigm where prompts drive the generation of user-specific outputs. However, this advancement has revealed a critical challenge: LLMs frequently produce outputs against socially acceptable commonsense standards in various scenarios. To address this gap in commonsense reasoning, we present KoCommonGEN v2, a fine-grained benchmark dataset focused on Korean commonsense reasoning. This dataset, enriched with human annotations, comprises multiple-choice questions across seven error categories. These categories include commonsense memorization, numerical commonsense, toxic speech, and more, which are vulnerable to undermining the reliability of LLMs' commonsense reasoning capabilities. The empirical results present that LLMs struggle with Korean commonsense reasoning. With human accuracy benchmarked at approximately 85%, GPT-4's performance lags at about 74%, and other LLMs demonstrate an average accuracy of around 42%. Our findings emphasize the need for targeted improvements in Korean commonsense reasoning within LLMs, paving the way for more socially and contextually sensitive AI models.

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.

Stories are rich in the emotions they exhibit in their narratives and evoke in the readers. The emotional journeys of the various characters within a story are central to their appeal. Computational analysis of the emotions of novels, however, has rarely examined the variation in the emotional trajectories of the different characters within them, instead considering the entire novel to represent a single story arc. In this work, we use character dialogue to distinguish between the emotion arcs of the narration and the various characters. We analyze the emotion arcs of the various characters in a dataset of English literary novels using the framework of Utterance Emotion Dynamics. Our findings show that the narration and the dialogue largely express disparate emotions through the course of a novel, and that the commonalities or differences in the emotional arcs of stories are more accurately captured by those associated with individual characters.

The Emotion Dynamics of Literary Novels

Geometry problem solving (GPS) is a challenging mathematical reasoning task requiring multi-modal understanding, fusion, and reasoning. Existing neural solvers take GPS as a vision-language task but are short in the representation of geometry diagrams that carry rich and complex layout information. In this paper, we propose a layout-aware neural solver named LANS, integrated with two new modules: multimodal layout-aware pre-trained language module (MLA-PLM) and layout-aware fusion attention (LA-FA). MLA-PLM adopts structural-semantic pre-training (SSP) to implement global relationship modeling, and point-match pre-training (PMP) to achieve alignment between visual points and textual points. LA-FA employs a layout-aware attention mask to realize point-guided cross-modal fusion for further boosting layout awareness of LANS. Extensive experiments on datasets Geometry3K and PGPS9K validate the effectiveness of the layout-aware modules and superior problem-solving performance of our LANS solver, over existing symbolic and neural solvers. We have made our code and data publicly available.

LANS: A Layout-Aware Neural Solver for Plane Geometry Problem

Rule-based reasoning, a fundamental type of legal reasoning, enables us to draw conclusions by accurately applying a rule to a set of facts. We explore causal language models as rule-based reasoners, specifically with respect to compositional rules - rules consisting of multiple elements which form a complex logical expression. Reasoning about compositional rules is challenging because it requires multiple reasoning steps, and attending to the logical relationships between elements. We introduce a new prompting method, Chain of Logic, which elicits rule-based reasoning through decomposition (solving elements as independent threads of logic), and recomposition (recombining these sub-answers to resolve the underlying logical expression). This method was inspired by the IRAC (Issue, Rule, Application, Conclusion) framework, a sequential reasoning approach used by lawyers. We evaluate chain of logic across eight rule-based reasoning tasks involving three distinct compositional rules from the LegalBench benchmark and demonstrate it consistently outperforms other prompting methods, including chain of thought and self-ask, using open-source and commercial language models.

Chain of Logic: Rule-Based Reasoning with Large Language Models

Do LMs infer the semantics of text from co-occurrence patterns in their training data? Merrill et al. (2022) argue that, in theory, sentence co-occurrence probabilities predicted by an optimal LM should reflect the entailment relationship of the constituent sentences, but it is unclear whether probabilities predicted by neural LMs encode entailment in this way because of strong assumptions made by Merrill et al. (namely, that humans always avoid redundancy). In this work, we investigate whether their theory can be used to decode entailment relations from neural LMs. We find that a test similar to theirs can decode entailment relations between natural sentences, well above random chance, though not perfectly, across many datasets and LMs. This suggests LMs implicitly model aspects of semantics to predict semantic effects on sentence co-occurrence patterns. However, we find the test that predicts entailment in practice works in the opposite direction to the theoretical test. We thus revisit the assumptions underlying the original test, finding its derivation did not adequately account for redundancy in human-written text. We argue that better accounting for redundancy related to *explanations* might derive the observed flipped test and, more generally, improve computational models of speakers in linguistics.

Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment

Psychological inoculation, a strategy designed to build resistance against persuasive misinformation, has shown efficacy in curbing its spread and mitigating its adverse effects at early stages. Despite its effectiveness, the design and optimization of these inoculations typically demand substantial human and financial resources, primarily due to the need for repeated experimental trials. To address these challenges, this paper introduces Simulated Misinformation Susceptibility Tests (SMISTs), leveraging Large Language Models (LLMs) to simulate participant responses in misinformation studies. SMIST employs a life experience-driven simulation methodology, which accounts for various aspects of participants' backgrounds, to mitigate common issues of caricatures and stereotypes in LLM simulations and enhance response diversity. Our extensive experimentation demonstrates that SMIST, utilizing GPT-4 as the backend model, yields results that align closely with those obtained from human-subject studies in misinformation susceptibility. This alignment suggests that LLMs can effectively serve as proxies in evaluating the impact of psychological inoculations. Moreover, SMIST offers the critical benefit of being applicable to emerging or anticipated misinformation scenarios without exposing human participants to potentially harmful content. This characteristic of SMIST not only preserves participant safety but also expands the scope of misinformation research to include more sensitive or speculative topics.

Simulated Misinformation Susceptibility (SMISTS): Enhancing Misinformation Research with Large Language Model Simulations

The rapid proliferation of online content necessitates effective summarization methods, among which dynamic aspect-based summarization stands out. Unlike its traditional counterpart, which assumes a fixed set of known aspects, this approach adapts to the varied aspects of the input text. We introduce a novel multi-objective learning framework employing a Longformer-Encoder-Decoder for this task. The framework optimizes aspect number prediction, minimizes disparity between generated and reference summaries for each aspect, and maximizes dissimilarity across aspect-specific summaries. Extensive experiments show our method significantly outperforms baselines on three diverse datasets, largely due to the effective alignment of generated and reference aspect counts without sacrificing single-aspect summarization quality.

MODABS: Multi-Objective Learning for Dynamic Aspect-Based Summarization

Real-world news comments pose a significant challenge due to their noisy and ambiguous nature, which complicates their modeling for clustering and summarization tasks. Most previous research has predominantly focused on extractive summarization methods within specific constraints. This paper concentrates on Clustering and Abstractive Summarization of online news Comments (CASC). First, we introduce an enhanced fast clustering algorithm that maintains a dynamic similarity threshold to ensure the high density of each comment cluster being built. Moreover, we pioneer the exploration of tuning Large Language Models (LLMs) through a chain-of-thought strategy to generate summaries for each comment cluster. On the other hand, a notable challenge in CASC research is the scarcity of evaluation data. To address this problem, we design an annotation scheme and contribute a manual test suite tailored for CASC. Experimental results on the test suite demonstrate the effectiveness of our improvements to the baseline methods. In addition, the quantitative and qualitative analyses illustrate the adaptability of our approach to real-world news comment scenarios.

Comprehensive Abstractive Comment Summarization with Dynamic Clustering and Chain of Thought

Zero-shot Relation Extraction (ZSRE) aims to predict unseen relations between entity pairs from input sentences. Existing prototype-based ZSRE methods encode relation descriptions into prototype embeddings and predict by measuring the similarity between sentence embeddings and prototype embeddings. However, these methods often overlook abundant side information of relations and suffer from a significant encoding gap between prototypes and sentences, limiting performance. To this end, we propose a framework named AlignRE, based on two Alignment methods for ZSRE. Specifically, we present a novel perspective centered on encoding schema alignment to enhance prototype-based ZSRE methods. We utilize well-designed prompt-tuning to bridge the encoding gap. To improve prototype quality, we explore and leverage multiple side information and propose a prototype aggregation method based on semantic alignment to create comprehensive relation prototype representations. We conduct experiments on FewRel and Wiki-ZSL datasets and consistently outperform state-of-the-art methods. Moreover, our method exhibits substantially faster performance and reduces the need for extensive manual labor in prototype construction. Code is available at https://github.com/lizehan1999/AlignRE.

AlignRE: An Encoding and Semantic Alignment Approach for Zero-Shot Relation Extraction

Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their deployment is still hindered by the vast model scale and computational costs. 
Post-training model pruning offers a way to compress LLMs. However, the current pruning methods designed for LLMs are not compatible with LoRA. This is due to their utilization of unstructured pruning on LLMs, impeding the merging of LoRA weights, or their dependence on the gradients of pre-trained weights to guide pruning, which can impose significant memory overhead.
To this end, we propose LoRAPrune, a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. Specifically, we first design a LoRA-guided pruning criterion, which uses the weights and gradients of LoRA, rather than the gradients of pre-trained weights for importance estimation. We subsequently integrate this criterion into an iterative pruning process, effectively removing redundant channels and heads. 
Extensive experimental results demonstrate the superior performance of our LoRAPrune over existing approaches on the LLaMA series models.
At a 50\% compression rate, LoRAPrune demonstrates superior performance over LLM-Pruner, achieving a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6\%.
Besides, LoRAPrune also matches semi-structural pruning across multiple LLMs, proving its wide applicability. The code is available at https://github.com/aim-uofa/LoRAPrune.

LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension $d$ in PLMs, a dimension critical to model size and efficiency. This paper introduces a novel structured pruning approach, Structured Pruning with PCA Projection ($\rm SP^3$), targeting the effective reduction of $d$ by projecting features into a space defined by principal components before masking. 
Extensive experiments on benchmarks (GLUE and SQuAD) show that \smodel can reduce $d$ by 70\%, compress 94\% of the $\rm BERT_{base}$ model, and maintain over 96\% accuracy and outperform other methods that compress $d$ by 6\% in accuracy at the same compression ratio. $\rm SP^3$ has also proven effective with other models, including OPT and Llama.
Our data and code are available at https://github.com/hyx1999/SP3

Premium content

KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models

Downloads

Next from ACL 2024

The Emotion Dynamics of Literary Novels

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES