Thailand

Despite the success of large language models (LLMs) in natural language generation, much evidence shows that LLMs may produce incorrect or nonsensical text. This limitation highlights the importance of discerning when to trust LLMs, especially in safety-critical domains. Existing methods often express reliability by confidence level, however, their effectiveness is limited by the lack of objective guidance. To address this, we propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD), which leverages reinforcement learning guided by a tailored dual-component reward function. This function integrates quality reward and order-preserving alignment reward functions. Specifically, the order-preserving reward incentivizes the model to verbalize greater confidence for responses of higher quality to align the order of confidence and quality. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy, without causing over-cautious. Furthermore, the aligned confidence provided by CONQORD informs when to trust LLMs, and acts as a determinant for initiating the retrieval process of external knowledge. Aligning confidence with response quality ensures more transparent and reliable responses, providing better trustworthiness.

ACL 2024

When to Trust LLMs: Aligning Confidence with Response Quality

trustworthiness in llms

confidence-quality alignment

reinforcement learning

### 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.

poster

This paper explores the application of synthetic data in the post-OCR domain on multiple fronts by conducting experiments to assess the impact of data volume, augmentation, and synthetic data generation methods on model performance. Furthermore, we introduce a novel algorithm that leverages computer vision feature detection algorithms to calculate glyph similarity for constructing post-OCR synthetic data. Through experiments conducted across a variety of languages, including several low-resource ones, we demonstrate that models like ByT5 can significantly reduce Character Error Rates (CER) without the need for manually annotated data, and our proposed synthetic data generation method shows advantages over traditional methods, particularly in low-resource languages.

Advancing Post-OCR Correction: A Comparative Study of Synthetic Data

Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces. Multimodal Large Language Models (MLLMs) have emerged as a promising solution to address these challenges, yet struggle with accurately interpreting human emotions and complex contents like misinformation. This paper introduces MM-Soc, a comprehensive benchmark designed to evaluate MLLMs' understanding of multimodal social media content. MM-Soc compiles prominent multimodal datasets and incorporates a novel large-scale YouTube tagging dataset, targeting a range of tasks from misinformation detection, hate speech detection, and social context generation. Through our exhaustive evaluation on ten size-variants of four open-source MLLMs, we have identified significant performance disparities, highlighting the need for advancements in models' social understanding capabilities. Our analysis reveals that, in a zero-shot setting, various types of MLLMs generally exhibit difficulties in handling social media tasks. However, MLLMs demonstrate performance improvements post fine-tuning, suggesting potential pathways for improvement.

MM-SOC: Benchmarking Multimodal Large Language Models in Social Media Platforms

Large Language Models (LLMs) have shown unprecedented performance in various real-world applications. However, they are known to generate factually inaccurate outputs, a.k.a. the hallucination problem. In recent years, incorporating external knowledge extracted from Knowledge Graphs (KGs) has become a promising strategy to improve the factual accuracy of LLM-generated outputs. Nevertheless, most existing explorations rely on LLMs themselves to perform KG knowledge extraction, which is highly inflexible as LLMs can only provide binary judgment on whether a certain knowledge (e.g., a knowledge path in KG) should be used. In addition, LLMs tend to pick only knowledge with direct semantic relationship with the input text, while potentially useful knowledge with indirect semantics can be ignored. In this work, we propose a principled framework KELP with three stages to handle the above problems. Specifically, KELP is able to achieve finer granularity of flexible knowledge extraction by generating scores for knowledge paths with input texts via latent semantic matching. Meanwhile, knowledge paths with indirect semantic relationships with the input text can also be considered via trained encoding between the selected paths in KG and the input text. Experiments on real-world datasets validate the effectiveness of KELP.

Knowledge Graph-Enhanced Large Language Models via Path Selection

Recently, there has been considerable attention on detecting hallucinations and omissions in Machine Translation (MT) systems. The two dominant approaches to tackle this task involve analyzing the MT system's internal states or relying on the output of external tools, such as sentence similarity or MT quality estimators. In this work, we introduce OTTAWA, a novel Optimal Transport (OT)-based word aligner specifically designed to enhance the detection of hallucinations and omissions in MT systems. Our approach explicitly models the missing alignments by introducing a "null" vector, for which we propose a novel one-side constrained OT setting to allow an adaptive null alignment. Our approach yields competitive results compared to state-of-the-art methods across 18 language pairs on the HalOmi benchmark. In addition, it shows promising features, such as the ability to distinguish between both error types and perform word-level detection without accessing the MT system's internal states.

OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection

While large language models (LLMs) excel in various natural language tasks in English, their performance in low-resource languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction.
In this paper, we address this evaluation and resource gap by introducing HeSum, a novel benchmark dataset specifically designed for Hebrew abstractive text summarization. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum's high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties even for state-of-the-art LLMs, establishing it as a valuable testbed for advancing generative language technology in Hebrew, and MRLs generative challenges in general.

HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew

Reasoning about time is essential for understanding the nuances of events described in natural language. Previous research on this topic has been limited in scope, characterized by a lack of standardized benchmarks that would allow for consistent evaluations across different studies. In this paper, we introduce TRAM, a temporal reasoning benchmark composed of ten datasets, encompassing various temporal aspects of events such as order, arithmetic, frequency, and duration, designed to facilitate a comprehensive evaluation of the TeR capabilities of large language models (LLMs). We evaluate popular LLMs like GPT-4 and Llama2 in zero-shot and few-shot scenarios, and establish baselines with BERT-based and domain-specific models. Our findings indicate that the best-performing model lags significantly behind human performance. It is our aspiration that TRAM will spur further progress in enhancing the TeR capabilities of LLMs.

TRAM: Benchmarking Temporal Reasoning for Large Language Models

Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effect should increase or decrease with the incorporation of strengthening arguments (supporters) or weakening arguments (defeaters), respectively. However, existing works ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defeasible settings. In this work, we present $\delta$-CAUSAL, the first benchmark dataset for studying defeasibility in causal reasoning. $\delta$-CAUSAL includes around 11K events spanning ten domains, featuring defeasible causality pairs, namely, cause-effect pairs accompanied by supporters and defeaters. We further show that current causal strength metrics fail to reflect the change of causal strength with the incorporation of supporters or defeaters in $\delta$-CAUSAL. To this end, we propose CESAR (Causal Embedding aSsociation with Attention Rating), a metric that measures causal strength based on token-level causal relationships. CESAR achieves a significant 69.7% relative improvement over existing metrics, increasing from 47.2% to 80.1% in capturing the causal strength change brought by supporters and defeaters. We further demonstrate even Large Language Models (LLMs) like GPT-3.5 still lag 4.5 and 10.7 points behind humans in generating supporters and defeaters, emphasizing the challenge posed by $\delta$-CAUSAL.

Exploring Defeasibility in Causal Reasoning

This paper introduces a multi-level, multi-label text classification dataset comprising over 3000 documents. The dataset features literary and critical texts from 19th-century Ottoman Turkish and Russian. It is the first study to apply large language models (LLMs) to this dataset, sourced from prominent literary periodicals of the era. The texts have been meticulously organized and labeled. This was done according to a taxonomic framework that takes into account both their structural and semantic attributes. Articles are categorized and tagged with bibliometric metadata by human experts. We present baseline classification results using a classical bag-of-words (BoW) naive Bayes model and three modern LLMs: multilingual BERT, Falcon, and Llama-v2. We found that in certain cases, Bag of Words (BoW) outperforms Large Language Models (LLMs), emphasizing the need for additional research, especially in low-resource language settings. This dataset is expected to be a valuable resource for researchers in natural language processing and machine learning, especially for historical and low-resource languages. The dataset is publicly available\footnote{\href{https://huggingface.co/nonwestlit}{https://huggingface.co/nonwestlit}. The dataset, code, and trained models are released under Apache 2.0 License.}.

A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts

This paper introduces ConceptMath, a bilingual (English and Chinese), ﬁne-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unlike traditional benchmarks that evaluate general mathematical reasoning with an average accuracy, ConceptMath systemically organizes math problems under a hierarchy of math concepts, so that mathematical reasoning can be evaluated at different granularity with concept-wise accuracies. Based on our ConcepthMath, we then evaluate a broad range of LLMs, and we observe existing LLMs, though achieving high average accuracies on traditional benchmarks, exhibit significant performance variations across different math concepts and may even fail catastrophically on the most basic ones. Besides, we also introduce an efﬁcient ﬁne-tuning strategy to enhance the weaknesses of existing LLMs. Finally, we hope ConceptMath could guide the developers to understand the ﬁne-grained mathematical abilities of their models and facilitate the growth of foundation models. Code is available at https://github.com/conceptmath/conceptmath.

ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models

Data augmentation methods have been a promising direction to improve the performance of small models for low-resource dialogue state tracking. However, traditional methods rely on pre-defined user goals and neglect the importance of data complexity in this task. In this paper, we propose EDZ-DA, an Easy-to-Difficult Zero-shot Data Augmentation framework for low-resource dialogue state tracking that utilizes large language models to automatically catch the relationships of different domains and then generate the dialogue data. We also complicate the dialogues based on the domain relation to enhance the model's capability for co-reference slot tracking. Furthermore, we permute slot values to mitigate the influence of output orders and the problem of incomplete value generation. Experimental results illustrate the superiority of our proposed method compared to previous strong data augmentation baselines on MultiWOZ.

Downloads

Next from ACL 2024

Advancing Post-OCR Correction: A Comparative Study of Synthetic Data

Similar lecture

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models