Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive volume of retrieved content, the possible dispersion of its parts, or their out of focus range may happen nevertheless to eventually have a detrimental rather than an incremental effect. To mitigate this issue and improve retrieval-augmented generation, we propose a method to refine the retrieved content before it is included in the prompt by resorting to meta-prompting optimization. Put to empirical test with the demanding multi-hop question answering task from the StrategyQA dataset, the evaluation results indicate that this method outperforms a similar retrieval-augmented system but without this method by over 30 %. Keywords: RAG Retrieval-Augmented Generation Prompt Optimization Large Language Models Meta-prompting Multi-hop QA

This paper presents CaseGPT, an innovative approach that combines Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) technology to enhance case-based reasoning in the healthcare and legal sectors. The system addresses the challenges of traditional database queries by enabling fuzzy searches based on imprecise descriptions, thereby improving data searchability and usability. CaseGPT not only retrieves relevant case data but also generates insightful suggestions and recommendations based on patterns discerned from existing case data. This functionality proves especially valuable for tasks such as medical diagnostics, legal precedent research, and case strategy formulation. The paper includes an in-depth discussion of the system's methodology, its performance in both medical and legal domains, and its potential for future applications. Our experiments demonstrate that CaseGPT significantly outperforms traditional keyword-based and simple LLM-based systems in terms of precision, recall, and efficiency.

In sentiment analysis of longer texts, there may be a variety of topics discussed, of entities mentioned, and of sentiments expressed regarding each entity. We find a lack of studies exploring how such texts express their sentiment towards each entity of interest, and how these sentiments can be modelled. In order to better understand how sentiment regarding persons and organizations (each entity in our scope) is expressed in longer texts, we have collected a dataset of expert annotations where the overall sentiment regarding each entity is identified, together with the sentence-level sentiment for these entities separately. We show that the reader's perceived sentiment regarding an entity often differs from an arithmetic aggregation of sentiments at the sentence level. Only 70\% of the positive and 55\% of the negative entities receive a correct overall sentiment label when we aggregate the (human-annotated) sentiment labels for the sentences where the entity is mentioned. Our dataset reveals the complexity of entity-specific sentiment in longer texts, and allows for more precise modelling and evaluation of such sentiment expressions.

Metaphors are part of everyday language and shape the way in which we conceptualize the world. Moreover, they play a multifaceted role in communication, making their understanding and generation a challenging task for language models (LMs). While there has been extensive work in the literature linking metaphor to the fulfilment of individual intentions, no comprehensive taxonomy of such intentions, suitable for natural language processing (NLP) applications, is available to present day. In this paper, we propose a novel taxonomy of intentions commonly attributed to metaphor, which comprises 9 categories. We also release the first dataset annotated for intentions behind metaphor use. Finally, we use this dataset to test the capability of large language models (LLMs) in inferring the intentions behind metaphor use, in zero- and in-context few-shot settings. Our experiments show that this is still a challenge for LLMs.

Introducing Entity-Aspect Sentiment Triplet Extraction (EASTE), a novel Aspect-Based Sentiment Analysis (ABSA) task which extends Target-Aspect-Sentiment Detection (TASD) by separating aspect categories (e.g., food#quality) into pre-defined entities (e.g., meal, drink) and aspects (e.g., taste, freshness) which add a fine-gainer level of complexity, yet help exposing true sentiment of chained aspect to its entity. We explore the task of EASTE solving capabilities of language models based on transformers architecture from our proposed unified-loss approach via token classification task using BERT architecture to text generative models such as Flan-T5, Flan-Ul2 to Llama2, Llama3 and Mixtral employing different alignment techniques such as zero/few-shot learning, Parameter Efficient Fine Tuning (PEFT) such as Low-Rank Adaptation (LoRA). The model performances are evaluated on the SamEval-2016 benchmark dataset representing the fair comparison to existing works. Our research not only aims to achieve high performance on the EASTE task but also investigates the impact of model size, type, and adaptation techniques on task performance. Ultimately, we provide detailed insights and achieving state-of-the-art results in complex sentiment analysis.

We consider the problem of adapting Large Language Models (LLMs) pre-trained with Reinforcement Learning from Human Feedback (RLHF) to downstream preference data. Naive approaches to achieve this could be supervised fine-tuning on preferred responses or reinforcement learning with a learned reward model. However, the LLM runs the risk of forgetting its initial knowledge as the fine-tuning progresses. To customize the LLM while preserving its existing capabilities, this paper proposes a novel method, named as Q-Adapter. We start by formalizing LLM adaptation as a problem of maximizing the linear combination of two rewards, one of which corresponds to the reward optimized by the pre-trained LLM and the other to the downstream preference data. Although both rewards are unknown, we show that this can be solved by directly learning a new module from the preference data that approximates the \emph{residual Q-function}. We consider this module to be an adapter because the original pre-trained LLM, together with it, can form the optimal customised LLM. Empirically, experiments on a range of domain-specific tasks and safety alignment tasks illustrate the superiority of Q-Adapter in both anti-forgetting and learning from new preferences.

Despite the growing interest in leveraging Large Language Models (LLMs) for content analysis, current studies have primarily focused on text-based content. In the present work, we explored the potential of LLMs in assisting video content analysis by conducting a case study that followed a new workflow of LLM-assisted multimodal content analysis. The workflow encompasses codebook design, prompt engineering, LLM processing, and human evaluation. We strategically crafted annotation prompts to get LLM Annotations in structured form and explanation prompts to generate LLM Explanations for a better understanding of LLM reasoning and transparency. To test LLM's video annotation capabilities, we analyzed 203 keyframes extracted from 25 YouTube short videos about depression. We compared the LLM Annotations with those of two human coders and found that LLM has higher accuracy in object and activity Annotations than emotion and genre Annotations. Moreover, we identified the potential and limitations of LLM's capabilities in annotating videos. Based on the findings, we explore opportunities and challenges for future research and improvements to the workflow. We also discuss ethical concerns surrounding future studies based on LLM-assisted video analysis.

This paper explores the biases in ChatGPT-based recommender systems, focusing on provider fairness (item-side fairness). Through extensive experiments and over a thousand API calls, we investigate the impact of prompt design strategies-including structure, system role, and intent-on evaluation metrics such as provider fairness, catalog coverage, temporal stability, and recency. The first experiment examines these strategies in classical top-K recommendations, while the second evaluates sequential in-context learning (ICL). In the first experiment, we assess seven distinct prompt scenarios on top-K recommendation accuracy and fairness. Accuracy-oriented prompts, like Simple and Chain-of-Thought (COT), outperform diversification prompts, which, despite enhancing temporal freshness, reduce accuracy by up to 50%. Embedding fairness into system roles, such as "act as a fair recommender," proved more effective than fairness directives within prompts. Diversification prompts led to recommending newer movies, offering broader genre distribution compared to traditional collaborative filtering (CF) models. The second experiment explores sequential ICL, comparing zero-shot and few-shot ICL. Results indicate that including user demographic information in prompts affects model biases and stereotypes. However, ICL did not consistently improve item fairness and catalog coverage over zero-shot learning. Zero-shot learning achieved higher NDCG and coverage, while ICL-2 showed slight improvements in hit rate (HR) when age-group context was included. Our study provides insights into biases of RecLLMs, particularly in provider fairness and catalog coverage. By examining prompt design, learning strategies, and system roles, we highlight the potential and challenges of integrating LLMs into recommendation systems. Further details can be found at https://github.com/yasdel/Benchmark_RecLLM_Fairness.

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same triggers as a certain class. Prior backdoor defense methods primarily target special token-based triggers, leaving syntax-based triggers insufficiently addressed. To fill this gap, this paper proposes a novel online defense algorithm that effectively counters syntax-based as well as special token-based backdoor attacks. The algorithm replaces semantically meaningful words in sentences with entirely different ones but preserves the syntactic templates or special tokens, and then compares the predicted labels before and after the substitution to determine whether a sentence contains triggers. Experimental results confirm the algorithm's performance against these two types of triggers, offering a comprehensive defense strategy for model integrity.

Symbolic sentence meaning representations, such as AMR (Abstract Meaning Representation) provide expressive and structured semantic graphs that act as intermediates that simplify downstream NLP tasks. However, the instruction-following capability of large language models (LLMs) offers a shortcut to effectively solve NLP tasks, questioning the utility of semantic graphs. Meanwhile, recent work has also shown the difficulty of using meaning representations merely as a helpful auxiliary for LLMs. We revisit the position of semantic graphs in syntactic simplification, the task of simplifying sentence structures while preserving their meaning, which requires semantic understanding, and evaluate it on a new complex and natural dataset. The AMR-based method that we propose, AMRS$^3$, demonstrates that state-of-the-art meaning representations can lead to easy-to-implement simplification methods with competitive performance and unique advantages in cost, interpretability, and generalization. With AMRS$^3$ as an anchor, we discover that syntactic simplification is a task where semantic graphs are helpful in LLM prompting. We propose AMRCoC prompting that guides LLMs to emulate graph algorithms for explicit symbolic reasoning on AMR graphs, and show its potential for improving LLM on semantic-centered tasks like syntactic simplification.