Malta

Agency, the capacity to proactively shape events, is central to how humans interact and collaborate. While LLMs are being developed to simulate human behavior and serve as human-like agents, little attention has been given to the Agency that these models should possess in order to proactively manage the direction of interaction and collaboration. In this paper, we investigate Agency as a desirable function of LLMs, and how it can be measured and managed. We build on social-cognitive theory to develop a framework of features through which Agency is expressed in dialogue -- indicating what you intend to do (Intentionality), motivating your intentions (Motivation), having self-belief in intentions (Self-Efficacy), and being able to self-adjust (Self-Regulation). We collect a new dataset of 83 human-human collaborative interior design conversations containing 908 conversational snippets annotated for Agency features. Using this dataset, we develop methods for measuring Agency of LLMs. Automatic and human evaluations show that models that manifest features associated with high Intentionality, Motivation, Self-Efficacy, and Self-Regulation are more likely to be perceived as strongly agentive.

EACL 2024

Investigating Agency of LLMs in Human-AI Collaboration Tasks

llms

human-ai collaboration

dialogue systems

poster

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode compositional representations of the concepts over which they operate, such as correctly identifying 'red cube' by reasoning over the constituents 'red' and 'cube'. In this work, we focus on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way (e.g., differentiating 'cube behind sphere' from 'sphere behind cube'). To inspect the performance of CLIP, we compare several architectures from research on compositional distributional semantics models (CDSMs), a line of research that attempts to implement traditional compositional linguistic structures within embedding spaces. We benchmark them on three synthetic datasets -- single-object, two-object, and relational -- designed to test concept binding. We find that CLIP can compose concepts in a single-object setting, but in situations where concept binding is needed, performance drops dramatically. At the same time, CDSMs also perform poorly, with best performance at chance level.

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

Recent advances in NLP have improved our ability to understand the nuanced worldviews of online communities. Existing research focused on probing ideological stances treats liberals and conservatives as separate groups. However, this fails to account for the nuanced views of the organically formed online communities and the connections between them. In this paper, we study discussions of the 2020 U.S. election on Twitter to identify complex interacting communities. Capitalizing on this interconnectedness, we introduce a novel approach that harnesses message passing when finetuning language models (LMs) to probe the nuanced ideologies of these communities. By comparing the responses generated by LMs and real-world survey results, our method shows higher alignment than existing baselines, highlighting the potential of using LMs in revealing complex ideologies within and across interconnected mixed-ideology communities.

Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communities

Knowledge-grounded dialogue generation is a challenging task because it requires satisfying two fundamental, yet often competing constraints: being responsive in a manner that is specific to what the conversation partner has said while also being attributable to an underlying source document. In this work, we bring this trade-off between these two objectives (specificity and attribution) to light, and ask the question: Can explicit content planning before the response generation help the model to address this challenge? To answer this question, we design a framework called PLEDGE, which allows us to experiment with various plan variables explored in prior work supporting both metric-agnostic and metric-aware approaches. While content planning shows promise, our results on whether it can actually help to navigate this trade-off are mixed -- planning mechanisms that are metric-aware (use automatic metrics during training) are better at automatic evaluations but underperform in human judgment compared to metric-agnostic mechanisms. We discuss how this may be caused by over-fitting to automatic metrics, and the need for future work to better calibrate these metrics towards human judgment. We hope the observations from our analysis will inform future work that aims to apply content planning in this context.

Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue

Automated story generation has been one of the long-standing challenges in NLP. Among all dimensions of stories, *suspense* is very common in human-written stories but relatively under-explored in AI-generated stories. While recent advances in large language models (LLMs) have greatly promoted language generation in general, state-of-the-art LLMs are still unreliable when it comes to suspenseful story generation. We propose a novel iterative-prompting-based planning method that is grounded in two theoretical foundations of story suspense from cognitive psychology and narratology. This theory-grounded method works in a fully zero-shot manner and does not rely on any supervised story corpora. To the best of our knowledge, this paper is the first attempt at suspenseful story generation with LLMs. Extensive human evaluations of the generated suspenseful stories demonstrate the effectiveness of our method.

Creating Suspenseful Stories: Iterative Planning with Large Language Models

In real-world scenarios, labeled samples for dialogue summarization are usually limited (i.e., few-shot) due to high annotation costs for high-quality dialogue summaries. To efficiently learn from few-shot samples, previous works have utilized massive annotated data from other downstream tasks and then performed prompt transfer in prompt tuning so as to enable cross-task knowledge transfer. However, existing general-purpose prompt transfer techniques lack consideration for dialogue-specific information. In this paper, we focus on improving the prompt transfer from dialogue state tracking to dialogue summarization and propose Skeleton-Assisted Prompt Transfer (SAPT), which leverages skeleton generation as extra supervision that functions as a medium connecting the distinct source and target task and resulting in the model's better consumption of dialogue state information. To automatically extract dialogue skeletons as supervised training data for skeleton generation, we design a novel approach with perturbation-based probes requiring neither annotation effort nor domain knowledge. Training the model on such skeletons can also help preserve model capability during prompt transfer. Our method significantly outperforms existing baselines. In-depth analyses demonstrate the effectiveness of our method in facilitating cross-task knowledge transfer in few-shot dialogue summarization.

Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning

Recent advancements in Large Language Models (LLMs) have heralded unprecedented capabilities in information-seeking and text generation, as evidenced by applications like Bing Chat and perplexity.ai. Despite these strides, challenges on hallucination and factual inconsistency continue to impede their wider real-world adoption. Contemporary methods, including retrieval-augmented LLMs and feedback-based learning, serve as alternatives to mitigate these challenges. However, challenges remain, particularly regarding referencing erroneous evidence (citation errors) and generating information not present in the evidence (hallucination). In this paper, we introduce the $\mathsf{A}^2\mathsf{R}$ framework: \textbf{\underline{A}}sk, \textbf{\underline{A}}ssess, and \textbf{\underline{R}}efine. Our approach utilizes an \textit{explicit} evaluation paradigm, incorporating metrics specifically tailored to assess citation errors and hallucination, aiming to address these prevalent challenges robustly. Capitalizing on these evaluations, we devise a strategy to formulate actionable natural language feedback, enabling iterative refinements that yield improved factual consistency and reduced hallucinations in responses. Our experiments on ASQA, ELI5, and QAMPARI datasets demonstrate our method's superiority in enhancing correctness, fluency, and citation quality.

Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning

Relations such as "is influenced by", "is known for" or "is a competitor of" are inherently graded: we can rank entity pairs based on how well they satisfy these relations, but it is hard to draw a line between those pairs that satisfy them and those that do not. Such graded relations play a central role in many applications, yet they are typically not covered by existing Knowledge Graphs. In this paper, we consider the possibility of using Large Language Models (LLMs) to fill this gap. To this end, we introduce a new benchmark, in which entity pairs have to be ranked according to how much they satisfy a given graded relation. The task is formulated as a few-shot ranking problem, where models only have access to a description of the relation and five prototypical instances. We use the proposed benchmark to evaluate state-of-the-art relation embedding strategies as well as several publicly available LLMs and closed conversational models such as GPT-4. We find that smaller language models struggle to outperform a naive baseline. Overall, the best results are obtained with the 11B parameter Flan-T5 model and the 13B parameter OPT model, where further increasing the model size does not seem to be beneficial. For all models, a clear gap with human performance remains.

A RelEntLess Benchmark for Modelling Graded Relations between Named Entities

Natural language (NL) feedback offers rich insights into user experience. While existing studies focus on an instance-level approach, where feedback is used to refine specific examples, we introduce a framework for system-level use of NL feedback. We show how to use feedback to formalize system-level design decisions in a human-in-the-loop-process -- in order to produce better models. In particular this is done through: (i) metric design for tasks; and (ii) language model prompt design for refining model responses. We conduct two case studies of this approach for improving search query and dialog response generation, demonstrating the effectiveness of system-level feedback. We show the combination of system-level and instance-level feedback brings further gains, and that human written instance-level feedback results in more grounded refinements than GPT-3.5 written ones, underlying the importance of human feedback for building systems.

System-Level Natural Language Feedback

Sentiment analysis is a crucial task in natural language processing that involves identifying and extracting subjective sentiment from text. Self-training has recently emerged as an economical and efficient technique for developing sentiment analysis models by leveraging a small amount of labeled data and a large amount of unlabeled data. However, given a set of training data, how to utilize them to conduct self-training makes a significant difference in the final performance of the model. We refer to this methodology as the self-training strategy. In this paper, we present an empirical study of various self-training strategies for sentiment analysis. First, we investigate the influence of the self-training strategy and hyper-parameters on the performance of traditional small language models (SLMs) in various few-shot settings. Second, we also explore the feasibility of leveraging large language models (LLMs) to help self-training. We propose and empirically compare several self-training strategies with the intervention of LLMs. Extensive experiments are conducted on three real-world sentiment analysis datasets.

Self-training Strategies for Sentiment Analysis: An Empirical Study

Empathy – encompassing the understanding and supporting others' emotions and perspectives – strengthens various social interactions, including written communication in healthcare, education and journalism. Detecting empathy using AI models by relying on self-assessed ground truth through crowdsourcing is challenging due to the inherent noise in such annotations. To this end, we propose a novel system, named Large Language Model-Guided Empathy _(LLM-GEm)_ prediction system. It rectifies annotation errors based on our defined annotation selection threshold and makes the annotations reliable for conventional empathy prediction models, e.g., BERT-based pre-trained language models (PLMs). Previously, demographic information was often integrated numerically into empathy detection models. In contrast, our _LLM-GEm_ leverages GPT-3.5 LLM to convert numerical data into semantically meaningful textual sequences, enabling seamless integration into PLMs. We experiment with three _NewsEmpathy_ datasets involving people's empathy levels towards newspaper articles and achieve state-of-the-art test performance using a RoBERTa-based PLM. Code and evaluations are publicly available at [https://github.com/hasan-rakibul/LLM-GEm](https://github.com/hasan-rakibul/LLM-GEm).

Premium content

Investigating Agency of LLMs in Human-AI Collaboration Tasks

Downloads

Next from EACL 2024

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES