Illusions of causality occur when people develop the belief that there is a causal connection between two variables with no supporting evidence. This cognitive bias has been proposed to underlie many societal problems including social prejudice, stereotype formation, misinformation and superstitious thinking. In this research we investigate whether large language models develop the illusion of causality in real-world settings. We evaluated and compared news headlines generated by GPT-4o-Mini, Claude-3.5-Sonnet, and Gemini-1.5-Pro to determine whether the models incorrectly framed correlations as causal relationships. In order to also measure sycophantic behavior, which occurs when a model aligns with a user's beliefs in order to look favorable even if it is not objectively correct, we additionally incorporated the bias into the prompts, observing if this manipulation increases the likelihood of the models exhibiting the illusion of causality. We found that Claude-3.5-Sonnet is the model that presents the lowest degree of causal illusion aligned with experiments on Correlation-to-Causation Exaggeration in human-written press releases. On the other hand, our findings suggest that while mimicry sycophancy increases the likelihood of causal illusions in these models, especially in GPT-4o-Mini, Claude-3.5-Sonnet remains the most robust against this cognitive bias.

Recent progress in audio-language modeling, such as automated audio captioning, has benefited from training on synthetic data generated with the aid of large-language models. However, such approaches for environmental sound captioning have primarily focused on audio event tags and have not explored leveraging emotional information that may be present in recordings. In this work, we explore the benefit of generating emotion-augmented synthetic audio caption data by instructing ChatGPT with additional acoustic information in the form of estimated soundscape emotion. To do so, we introduce EmotionCaps, an audio captioning dataset comprised of approximately 120,000 audio clips with paired synthetic descriptions enriched with soundscape emotion recognition (SER) information. We hypothesize that this additional information will result in higher-quality captions that match the emotional tone of the audio recording, which will, in turn, improve the performance of captioning models trained with this data. We test this hypothesis through both objective and subjective evaluation, comparing models trained with the EmotionCaps dataset to multiple baseline models. Our findings challenge current approaches to captioning and suggest new directions for developing and assessing captioning models.

We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investigate the impact of injecting diverse persona descriptions into LLM prompts across two studies, exploring whether personas increase annotation diversity and whether the impacts of individual personas on the resulting annotations are consistent and controllable. Our results show that persona-prompted LLMs produce more diverse annotations than LLMs prompted without personas and that these effects are both controllable and repeatable, making our approach a suitable tool for improving data annotation in subjective NLP tasks like toxicity detection.

This study offers an initial evaluation of a human-in-the-loop system leveraging GPT-4 (a large language model or LLM), and Retrieval-Augmented Generation (RAG) to identify and define jargon terms in scientific abstracts, based on readers' self-reported knowledge. The system achieves fairly high recall in identifying jargon and preserves relative differences in readers' jargon identification, suggesting personalization as a feasible use-case for LLMs to support sense-making of complex information. Surprisingly, using only abstracts for context to generate definitions yields slightly more accurate and higher quality definitions than using RAG-based context from the fulltext of an article. The findings highlight the potential of generative AI for assisting science reporters, and can inform future work on developing tools to simplify dense documents.

This paper describes our $3^{rd}$ place submission in the AVeriTeC shared task in which we attempted to address the challenge of fact-checking with evidence retrieved in the wild using a simple scheme of Retrieval-Augmented Generation (RAG) designed for the task, leveraging the predictive power of Large Language Models. We release our codebase and explain its two modules - the Retriever and the Evidence & Label generator - in detail, justifying their features such as MMR-reranking and Likert-scale confidence estimation. We evaluate our solution on AVeriTeC dev and test set and interpret the results, picking the GPT-4o as the most appropriate model for our pipeline at the time of our publication, with Llama 3.1 70B being a promising open-source alternative. We perform an empirical error analysis to see that faults in our predictions often coincide with noise in the data or ambiguous fact-checks, provoking further research and data augmentation.

Logical fallacy uses invalid or faulty reasoning in the construction of a statement. Despite the prevalence and harmfulness of logical fallacies, detecting and classifying logical fallacies still remains a challenging task. We observe that logical fallacies often use connective words to indicate an intended logical relation between two arguments, while the argument semantics does not actually support the logical relation. Inspired by this observation, we propose to build a logical structure tree to explicitly represent and track the hierarchical logic flow among relation connectives and their arguments in a statement. Specifically, this logical structure tree is constructed in an unsupervised manner guided by the constituency tree and a taxonomy of connectives for ten common logical relations, with relation connectives as non-terminal nodes and textual arguments as terminal nodes, and the latter are mostly elementary discourse units. We further develop two strategies to incorporate the logical structure tree into LLMs for fallacy reasoning. Firstly, we transform the tree into natural language descriptions and feed the textualized tree into LLMs as a part of the hard text prompt. Secondly, we derive a relation-aware tree embedding and insert the tree embedding into LLMs as a soft prompt. Experiments on benchmark datasets demonstrate that our approach based on logical structure tree significantly improves precision and recall for both fallacy detection and fallacy classification.

Recent research on query generation has focused on using Large Language Models (LLMs), which despite bringing state-of-the-art performance, also introduce issues with hallucinations in the generated queries. In this work, we introduce relevance hallucination and factuality hallucination as a new typology for hallucination problems brought by query generation based on LLMs. We propose an effective way to separate content from form in LLM-generated queries, which preserves the factual knowledge extracted and integrated from the inputs and compiles the syntactic structure, including function words, using the powerful linguistic capabilities of the LLM. Specifically, we introduce a model-agnostic and training-free method that turns the Large Language Model into a Pointer-Generator (LargePiG), where the pointer attention distribution leverages the LLM's inherent attention weights, and the copy probability is derived from the difference between the vocabulary distribution of the model's high layers and the last layer. To validate the effectiveness of LargePiG, we constructed two datasets for assessing the hallucination problems in query generation, covering both document and video scenarios. Empirical studies on various LLMs demonstrated the superiority of LargePiG on both datasets. Additional experiments also verified that LargePiG could reduce hallucination in large vision language models and improve the accuracy of document-based question-answering and factuality evaluation tasks.

Traditional Retrieval-Augmented Generation (RAG) methods are limited by their reliance on a fixed number of retrieved documents, often resulting in incomplete or noisy information that undermines task performance. Although recent adaptive approaches alleviated these problems, their application in intricate and real-world multimodal tasks remains limited. To address these, we propose a new approach called Self-adaptive Multimodal Retrieval-Augmented Generation (SAM-RAG), tailored specifically for multimodal contexts. SAM-RAG not only dynamically filters relevant documents based on the input query, including image captions when needed, but also verifies the quality of both the retrieved documents and the output. Extensive experimental results show that SAM-RAG surpasses existing state-of-the-art methods in both retrieval accuracy and response generation. By further ablation experiments and effectiveness analysis, SAM-RAG maintains high recall quality while improving overall task performance in multimodal RAG task. Our codes are available at https://github.com/SAM-RAG/SAM_RAG.

Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy in real-world applications, highlighting the importance of compressing them. To achieve this goal, knowledge distillation (KD) is a common approach, which aims to distill the larger teacher model into a smaller student model. While numerous KD methods for autoregressive LLMs have emerged recently, it is still under-explored whether they work well in complex text-to-SQL scenarios. To this end, we conduct a series of analyses and reveal that these KD methods generally fall short in balancing performance and efficiency. In response to this problem, we propose to improve the KD with Imperfect Data, namely KID, which effectively boosts the performance without introducing much training budget. The core of KID is to efficiently mitigate the training-inference mismatch by simulating the cascading effect of inference in the imperfect training data. Extensive experiments on 5 text-to-SQL benchmarks show that, KID can not only achieve consistent and significant performance gains (up to +5.83% average score) across all model types and sizes, but also effectively improve the training efficiency.

This paper concerns the evaluation of reward models used in language modeling. A reward model is a function that takes a prompt and a response and assigns a score indicating how good that response is for the prompt. A key challenge is that reward models are usually imperfect proxies for actual preferences. For example, we may worry that a model trained to reward helpfulness learns to instead prefer longer responses. In this paper, we develop an evaluation method, RATE (Rewrite-based Attribute Treatment Estimators), that allows us to measure the causal effect of a given attribute of a response (e.g., length) on the reward assigned to that response. The core idea is to use large language models to rewrite responses to produce imperfect counterfactuals, and to adjust for rewriting error by rewriting twice. We show that the RATE estimator is consistent under reasonable assumptions. We demonstrate the effectiveness of RATE on synthetic and real-world data, showing that it can accurately estimate the effect of a given attribute on the reward model.