Thailand

We observe that current large language models often waver in their judgments when faced with follow-up questions, even if the original judgment was correct. This wavering presents a significant challenge for generating reliable responses and building user trust. To comprehensively assess this issue, we introduce a \textsc{Follow-up Questioning Mechanism} along with two metrics to quantify this inconsistency, confirming its widespread presence in current large language models. Furthermore, to mitigate this issue, we explore various prompting strategies for closed-source models, and develop a training-based framework \textsc{Unwavering-FQ} that teaches large language models to maintain their originally correct judgments through synthesized high-quality preference data. Our experimental results confirm the effectiveness of our framework and its ability to enhance the general capabilities of large language models.

ACL 2024

Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment

judgment consistency

alignment

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.

Incrementally expanding the capability of an existing translation model to solve new domain tasks over time is a fundamental and practical problem, which usually suffers from catastrophic forgetting. Generally, multi-domain learning can be seen as a good solution. However, there are two drawbacks: 1) it requires having the training data for all domains available at the same time, which may be unrealistic due to storage or privacy concerns; 2) it requires re-training the model on the data of all domains from scratch when adding a new domain and this is time-consuming and computationally expensive. To address these issues, we present a semi-supervised contrastive distillation framework for incremental neural machine translation. Specifically, to avoid catastrophic forgetting, we propose to exploit unlabeled data from the same distributions of the older domains through knowledge distillation. Further, to ensure the distinct domain characteristics in the model as the number of domains increases, we devise a cross-domain contrastive objective to enhance the distilled knowledge. Extensive experiments on domain translation benchmarks show that our approach, without accessing any previous training data or re-training on all domains from scratch, can significantly prevent the model from forgetting previously learned knowledge while obtaining good performance on the incrementally added domains. The code and data with step-by-step instructions will be released upon acceptance.

Continual Learning with Semi-supervised Contrastive Distillation for Incremental Neural Machine Translation

The process of meaning composition, wherein smaller units like morphemes or words combine to form the meaning of phrases and sentences, is essential for human sentence comprehension. Despite extensive neurolinguistic research into the brain regions involved in meaning composition, a computational metric to quantify the extent of composition is still lacking. Drawing on the key-value memory interpretation of transformer feed-forward network blocks, we introduce the Composition Score, a novel model-based metric designed to quantify the degree of meaning composition during sentence comprehension. Experimental findings show that this metric correlates with brain clusters associated with word frequency, structural processing, and general sensitivity to words, suggesting the multifaceted nature of meaning composition during human sentence comprehension.

Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models

The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recently shown to improve the faithfulness, grounding, and controllability of generated text. We conceptualize plans as a sequence of questions which serve as blueprints of the generated content and its organization. We propose two attribution models that utilize different variants of blueprints, an abstractive model where questions are generated from scratch, and an extractive model where questions are copied from the input. Experiments on long-form question-answering show that planning consistently improves attribution quality. Moreover, the citations generated by blueprint models are more accurate compared to those obtained from LLM-based pipelines lacking a planning component.

Learning to Plan and Generate Text with Citations

In this study, we explore in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting tailored for the EAE task. Specifically, we hypothesize and validate that LLMs learn task-specific heuristics from demonstrations in ICL. Building upon this hypothesis, we introduce an explicit heuristic-driven demonstration construction approach, which transforms the haphazard example selection process into a systematic method that emphasizes task heuristics. Additionally, inspired by the analogical reasoning of human, we propose the link-of-analogy prompting, which enables LLMs to process new situations by drawing analogies to known situations, enhancing their performance on unseen classes beyond limited ICL examples. Experiments show that our method outperforms existing prompting methods and few-shot supervised learning methods on document-level EAE datasets. Additionally, the HD-LoA prompting shows effectiveness in other tasks like sentiment analysis and natural language inference, demonstrating its broad adaptability.

LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction

Neural machine translation systems estimate probabilities of target sentences given source sentences, yet these estimates may not align with human preferences. This work introduces QE-fusion, a method that synthesizes translations using a quality estimation metric (QE), which correlates better with human judgments. QE-fusion leverages a pool of candidates sampled from a model, combining spans from different candidates using a QE metric such as CometKiwi. We compare QE-fusion against beam search and recent reranking techniques, such as Minimum Bayes Risk decoding or QE-reranking. Our method consistently improves translation quality in terms of COMET and BLEURT scores when applied to large language models (LLMs) used for translation (PolyLM, XGLM, Llama2, Mistral, ALMA, and Tower) and to multilingual translation models (NLLB), over five language pairs. Notably, QE-fusion exhibits larger improvements for LLMs due to their ability to generate diverse outputs. We demonstrate that our approach generates novel translations in over half of the cases and consistently outperforms other methods across varying numbers of candidates (5–200). Furthermore, we empirically establish that QE-fusion scales linearly with the number of candidates in the pool.

Don’t Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning LLMs when provided parallel training data. To address these challenges, we propose LANDeRMT, a Language-Aware Neuron Detecting and Routing framework that selectively finetunes LLMs to Machine Translation with diverse translation training data. In LANDeRMT, we evaluate the awareness of neurons to MT tasks and categorize them into language-general and language-specific neurons. This categorization enables selective parameter updates during finetuning, mitigating parameter interference and catastrophic forgetting issues. For the detected neurons, we further propose a conditional awareness-based routing mechanism to dynamically adjust language-general and language-specific capacity within LLMs, guided by translation signals. Experimental results demonstrate that the proposed LANDeRMT is very effective in learning translation knowledge, significantly improving translation quality over various strong baselines for multiple language pairs.

LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation

Humans understand sentences word-by-word, in the order that they hear them. This incrementality entails resolving temporary ambiguities about syntactic relationships. We investigate how humans process these syntactic ambiguities by correlating predictions from incremental generative dependency parsers with timecourse data from people undergoing functional neuroimaging while listening to an audiobook. In particular, we compare competing hypotheses regarding the number of developing syntactic analyses in play during word-by-word comprehension: one vs more than one. This comparison involves evaluating syntactic surprisal from a state-of-the-art dependency parser with LLM-adapted encodings against an existing fMRI dataset. In both English and Chinese data, we find evidence for multipath parsing. Brain regions associated with this multipath effect include bilateral superior temporal gyrus.

Multipath parsing in the brain

The boardgame Diplomacy is a challenging setting for communicative and cooperative artificial intelligence. The most prominent communicative Diplomacy AI, Cicero, has excellent strategic abilities, exceeding human players. However, the best Diplomacy players master communication, not just tactics, which is why the game has received attention as an AI challenge. This work seeks to understand the degree to which Cicero succeeds at communication. First, we annotate in-game communication with abstract meaning representation to separate in-game tactics from general language. Second, we run two dozen games with humans and Cicero, totaling over 200 human-player hours of competition. While AI can consistently outplay human players, AI-Human communication is still limited because of AI’s difficulty with deception and persuasion. This shows that Cicero relies on strategy and has not yet reached the full promise of communicative and cooperative AI.

More Victories, Less Cooperation: Assessing Cicero’s Diplomacy Play

A dog whistle is a form of coded communication that carries a secondary meaning to specific audiences and is often weaponized for racial and socioeconomic discrimination. Dog whistling historically originated from United States politics, but in recent years has taken root in social media as a means of evading hate speech detection systems and maintaining plausible deniability. In this paper, we present an approach for word-sense disambiguation of dog whistles from standard speech using Large Language Models (LLMs), and leverage this technique to create a dataset of 16,550 high-confidence coded examples of dog whistles used in formal and informal communication. Silent Signals is the largest dataset of disambiguated dog whistle usage, created for applications in hate speech detection, neology, and political science.

Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles

Theory of Mind (ToM), the ability to understand people’s mental states, is an essential ingredient for developing machines with human-level social intelligence. Recent machine learning models, particularly large language models, seem to show some aspects of ToM understanding. However, existing ToM benchmarks use unimodal datasets – either video or text. Human ToM, on the other hand, is more than video or text understanding. People can flexibly reason about another person’s mind based on conceptual representations (e.g., goals, beliefs, plans) extracted from any available data. To address this, we introduce a multimodal Theory of Mind question answering (MMToM-QA) benchmark. MMToM-QA comprehensively evaluates machine ToM both on multimodal data and on different kinds of unimodal data about a person’s activity in a household environment. To engineer multimodal ToM capacity, we propose a novel method, BIP-ALM (Bayesian Inverse Planning Accelerated by Language Models). BIP-ALM extracts unified representations from multimodal data and utilizes language models for scalable Bayesian inverse planning. We conducted a systematic comparison of human performance, BIP-ALM, and state-of-the-art models, including GPT-4. The experiments demonstrate that large language models and large multimodal models still lack robust ToM capacity. BIP-ALM, on the other hand, shows promising results, by leveraging the power of both model-based mental inference and language models.

Premium content

Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment

Downloads

Next from ACL 2024

Continual Learning with Semi-supervised Contrastive Distillation for Incremental Neural Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES