Thailand

We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from structured data. To avoid the issue of LLM training data contamination with standard benchmarks, we design Quintd - a tool for collecting novel structured data records from public APIs. We find that open LLMs (Llama 2, Mistral, and Zephyr) can generate fluent and coherent texts in zero-shot settings from data in common formats collected with Quintd. However, we show that the semantic accuracy of the outputs is a major issue: both according to human annotators and our reference-free metric based on GPT-4, more than 80% of the outputs of open LLMs contain at least one semantic error. We publicly release the code, data, and model outputs.

ACL 2024

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

open llm

data-to-text

evaluation

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.

Explanations for AI should aid human users, yet this ultimate goal remains under-explored. This paper aims to bridge this gap by investigating the specific explanatory needs of human users in the context of Knowledge Graph Completion (KGC) systems. In contrast to the prevailing approaches that primarily focus on mathematical theories, we recognize the potential limitations of explanations that may end up being overly complex or nonsensical for users. Through in-depth user interviews, we gain valuable insights into the types of KGC explanations users seek. Building upon these insights, we introduce GradPath, a novel path-based explanation method designed to meet human-centric explainability constraints and enhance plausibility. Additionally, GradPath harnesses the gradients of the trained KGC model to maintain a certain level of faithfulness. We verify the effectiveness of GradPath through well-designed human-centric evaluations. The results confirm that our method provides explanations that users consider more plausible than previous ones.

Generating and Evaluating Plausible Explanations for Knowledge Graph Completion

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of the information from the relevant query-corpus paired data can further boost the LLM capabilities. In this paper, we propose a novel method, Search-Adaptor, for customizing LLMs for information retrieval in an efficient and robust way. Search-Adaptor modifies the embeddings generated by pre-trained LLMs, and can be integrated with any LLM, including those only available via prediction APIs. On multiple English, multilingual, and multimodal retrieval datasets, we show consistent and significant performance benefits for Search-Adaptor -- e.g., more than 5% improvements for Google Embedding APIs in nDCG@10 averaged over 14 BEIR datasets.

Search-Adaptor: Embedding Customization for Information Retrieval

This paper proposes PiNose, which trains a probing model on offline self-consistency checking results, thereby circumventing the need for human-annotated data and achieving transferability across diverse data distributions. As the consistency check process is offline, PiNose reduces the computational burden of generating multiple responses by online consistency verification. 

Additionally, it examines various aspects of internal states prior to response decoding, contributing to more effective detection of factual inaccuracies. 

Experiment results on both factuality detection and question answering benchmarks show that PiNose achieves surpassing results than existing factuality detection methods.

Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking

The performance of modern language models (LMs) has been improved by chain-of-thought (CoT) reasoning, i.e., the process of generating intermediate results that guide the model towards a final answer. A possible explanation for this improvement is that CoT reasoning extends an LM’s computational power, as RNNs and transformers with additional scratch space are known to be Turing complete. Comparing LMs to Turing machines, however, introduces a category error—Turing machines decide language membership, whereas LMs define distributions over strings. To bridge this gap, we formalize CoT reasoning in a probabilistic setting. We present several results on the representational capacity of recurrent and transformer LMs with CoT reasoning, showing that they can represent the same family of distributions over strings as probabilistic Turing machines.

On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning

Multimodal large language models (MLLMs) like LLaVA and GPT-4(V) enable general-purpose conversations about images with the language modality. As off-the-shelf MLLMs may have limited capabilities on images from domains like dermatology and agriculture, they must be fine-tuned to unlock domain-specific applications. The prevalent architecture of current open-source MLLMs comprises two major modules: an image-language (cross-modal) projection network and a large language model. It is desirable to understand the roles of these two modules in modeling domain-specific visual attributes to inform the design of future models and streamline the interpretability efforts on the current models. To this end, via experiments on 4 datasets and under 2 fine-tuning settings, we find that as the MLLM is fine-tuned, it indeed gains domain-specific visual capabilities, but the updates do not lead to the projection extracting relevant domain-specific visual attributes. Our results indicate that the domain-specific visual attributes are modeled by the LLM, even when only the projection is fine-tuned. Through this study, we offer a potential reinterpretation of the role of cross-modal projections in MLLM architectures.

Cross-Modal Projection in Multimodal LLMs Doesn’t Really Project Visual Attributes to Textual Space

Multistep instructions, such as recipes and how-to guides, greatly benefit from visual aids, such as a series of images that accompany the instruction steps. While Large Language Models (LLMs) have become adept at generating coherent textual steps, Large Vision/Language Models (LVLMs) are less capable of generating accompanying image sequences. The most challenging aspect is that each generated image needs to adhere to the relevant textual step instruction, as well as be visually consistent with earlier images in the sequence. To address this problem, we propose an approach for generating consistent image sequences, which integrates a Latent Diffusion Model (LDM) with an LLM to transform the sequence into a caption to maintain the semantic coherence of the sequence. In addition, to maintain the visual coherence of the image sequence, we introduce a copy mechanism to initialise reverse diffusion processes with a latent vector iteration from a previously generated image from a relevant step. Both strategies will condition the reverse diffusion process on the sequence of instruction steps and tie the contents of the current image to previous instruction steps and corresponding images. Experiments show that the proposed approach is preferred by humans in 46.6% of the cases against 26.6% for the second best method. In addition, automatic metrics showed that the proposed method maintains semantic coherence and visual consistency across steps in both domains.

Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks

To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perform this integration in a predictable way across different questions and contexts: models will rely more on prior knowledge for questions about entities (e.g., persons, places, etc.) that they are more familiar with due to higher exposure in the training corpus, and be more easily persuaded by some contexts than others. To formalize this problem, we propose two mutual information-based metrics to measure a model's dependency on a context and on its prior about an entity: first, the persuasion score of a given context represents how much a model depends on the context in its decision, and second, the susceptibility score of a given entity represents how much the model can be swayed away from its original answer distribution about an entity. We empirically test our metrics for their validity and reliability. Finally, we explore and find a relationship between the scores and the model's expected familiarity with an entity, and provide two use cases to illustrate their benefits.

Context versus Prior Knowledge in Language Models

Metaphor detection aims to identify whether a linguistic expression in text is metaphorical or literal. Most existing research tackles this problem either using word-pair or token-level information as input, and thus treats word-pair and token-level metaphor detection as distinct subtasks. Benefited from the simplified structure of word pairs, recent methods for word-pair metaphor detection can provide intermediate explainable clues for the detection results, which remains a challenging issue for token-level metaphor detection. To mitigate this issue in token-level metaphor detection and take advantage of word pairs, in this paper, we make the first attempt to bridge word-pair and token-level metaphor detection via modeling word pairs within a sentence as explainable intermediate information. As the central role of verb in metaphorical expressions, we focus on token-level verb metaphor detection and propose a novel explainable Word Pair based Domain Mining (WPDM) method. Our work is inspired by conceptual metaphor theory (CMT). We first devise an approach for conceptual domain mining utilizing semantic role mapping and resources at cognitive, commonsense and lexical levels. We then leverage the inconsistency between source and target domains for core word pair modeling to facilitate the explainability. Experiments on four datasets verify the effectiveness of our method and demonstrate its capability to provide the core word pair and corresponding conceptual domains as explainable clues for metaphor detection.

Bridging Word-Pair and Token-Level Metaphor Detection with Explainable Domain Mining

Embodied AI aims to develop robots that can \textit{understand} and execute human language instructions, as well as communicate in natural languages. On this front, we study the task of generating highly detailed navigational instructions for the embodied robots to follow. Although recent studies have demonstrated significant leaps in the generation of step-by-step instructions from sequences of images, the generated instructions lack variety in terms of their referral to objects and landmarks. Existing speaker models learn strategies to evade the evaluation metrics and obtain higher scores even for low-quality sentences. In this work, we propose SAS (Spatially-Aware Speaker), an instruction generator or \textit{Speaker} model that utilises both structural and semantic knowledge of the environment to produce richer instructions. For training, we employ a reward learning method in an adversarial setting to avoid systematic bias introduced by language evaluation metrics. Empirically, our method outperforms existing instruction generation models, evaluated using standard metrics. Our code is available at https://github.com/gmuraleekrishna/SAS.

Spatially-Aware Speaker for Vision-and-Language Navigation Instruction Generation

Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are taken at face value — we show this is a (potentially costly) mistake. Under existing leaderboards, the relative performance of LLMs is highly sensitive to (often minute) details. We show that for popular multiple-choice question benchmarks (e.g., MMLU), minor perturbations to the benchmark, such as changing the order of choices or the method of answer selection, result in changes in rankings up to 8 positions. We explain this phenomenon by conducting systematic experiments over three broad categories of benchmark perturbations and identifying the sources of this behavior. Our analysis results in several best-practice recommendations, including the advantage of a *hybrid* scoring method for answer selection. Our study highlights the dangers of relying on simple benchmark evaluations and charts the path for more robust evaluation schemes on the existing benchmarks. The code for this paper is available at [https://github.com/National-Center-for-AI-Saudi-Arabia/lm-evaluation-harness](https://github.com/National-Center-for-AI-Saudi-Arabia/lm-evaluation-harness).

Premium content

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

Downloads

Next from ACL 2024

Generating and Evaluating Plausible Explanations for Knowledge Graph Completion

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES