Since the dawn of the digitalisation era, customer feedback and online reviews are unequivocally major sources of insights for businesses. Consequently, conducting comparative analyses of such sources has become the de facto modus operandi of any business that wishes to give itself a competitive edge over its peers and improve customer loyalty. Sentiment analysis is one such method instrumental in gauging public interest, exposing market trends, and analysing competitors. While traditional sentiment analysis focuses on overall sentiment, as the needs advance with time, it has become important to explore public opinions and sentiments on various specific subjects, products and services mentioned in the reviews on a finer-granular level. To this end, Aspect-based Sentiment Analysis (ABSA), supported by advances in Artificial Intelligence (AI) techniques which have contributed to a paradigm shift from simple word-level analysis to tone and context-aware analyses, focuses on identifying specific aspects within the text and determining the sentiment associated with each aspect. In this study, we compare several deep-NN methods for ABSA on two benchmark datasets (Restaurant14 and Laptop-14) and found that FAST LSA obtains the best overall results of 87.6% and 82.6% accuracy but does not pass LSA+DeBERTa which reports 90.33% and 86.21% accuracy respectively.

Retrieval-augmented generation integrates the capabilities of large language models with relevant information retrieved from an extensive corpus, yet encounters challenges when confronted with real-world noisy data. One recent solution is to train a filter module to find relevant content but only achieve suboptimal noise compression. In this paper, we propose to introduce the information bottleneck theory into retrieval-augmented generation. Our approach involves the filtration of noise by simultaneously maximizing the mutual information between compression and ground output, while minimizing the mutual information between compression and retrieved passage. In addition, we derive the formula of information bottleneck to facilitate its application in novel comprehensive evaluations, the selection of supervised fine-tuning data, and the construction of reinforcement learning rewards. Experimental results demonstrate that our approach achieves significant improvements across various question answering datasets, not only in terms of the correctness of answer generation but also in the conciseness with $2.5\%$ compression rate.

A diverse range of large language models (LLMs), e.g., ChatGPT, and visual question answering (VQA) models, e.g., BLIP, have been developed for solving textual and visual question answering tasks. However, both LLMs and VQA models encounter challenges when applied to task-specific datasets. Fine-tuning these models is either difficult, as it requires access via APIs, rendering them as black-boxes, or costly due to the need of tuning a large number of parameters. To address this, we introduce InfoSel, a data-efficient and lightweight ensemble method that learns to dynamically pick the winner from existing black-box models for predictions on both textual and multimodal visual question answering tasks. Unlike traditional ensemble models, InfoSel does not rely on prediction probabilities or confidences, which typically are not available in black-box models. Experimental results on four datasets demonstrate that our approach achieves an absolute increase of up to +5.27% in the F1-score compared to standalone LLMs. Remarkably, this improvement is achieved by utilizing only 1K training instances and 110M model parameters for training task-specific ensemble models.

Nursing notes, an important component of Electronic Health Records (EHRs), keep track of the progression of a patient's health status during a care episode. Distilling the key information in nursing notes through text summarization techniques can improve clinicians' efficiency in understanding patients' conditions when reviewing nursing notes. However, existing abstractive summarization methods in the clinical setting have often overlooked nursing notes and require the creation of reference summaries for supervision signals, which is time-consuming. In this work, we introduce QGSumm, a query-guided self-supervised domain adaptation framework for nursing note summarization. Using patient-related clinical queries as guidance, our approach generates high-quality, patient-centered summaries without relying on reference summaries for training. Through automatic and manual evaluation by an expert clinician, we demonstrate the strengths of our approach compared to the state-of-the-art Large Language Models (LLMs) in both zero-shot and few-shot settings. Ultimately, our approach provides a new perspective on conditional text summarization, tailored to the specific interests of clinical personnel.

There has been a surge of interest in computational modeling of semantic change. The foci of previous works are on detecting and interpreting word senses gained over time; however, it remains unclear whether the gained senses are covered by dictionaries. In this work, we aim to fill this research gap by comparing detected word senses with dictionary sense inventories in order to bridge between the communities of lexical semantic change detection and lexicography. We evaluate our system in the AXOLOTL-24 shared task for Finnish, Russian and German languages \cite{fedorova-etal-2024-axolotl}. Our system is fully unsupervised. It leverages a graph-based clustering approach to predict mappings between unknown word usages and dictionary entries for Subtask 1, and generates dictionary-like definitions for those novel word usages through the state-of-the-art Large Language Models such as GPT-4 and LLaMA-3 for Subtask 2. In Subtask 1, our system outperforms the baseline system by a large margin, and it offers interpretability for the mapping results by distinguishing between matched and unmatched (novel) word usages through our graph-based clustering approach. Our system ranks first in Finnish and German, and ranks second in Russian on the Subtask 2 test-phase leaderboard. These results show the potential of our system in managing dictionary entries, particularly for updating dictionaries to include novel sense entries. Our code and data are made publicly available\footnote{\url{https://github.com/xiaohemaikoo/axolotl24-ABDN-NLP}}.

--While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation. We first let LLMs classify the type of the circuit based on the specifications. Then, according to the type of the circuit, we split the tasks into several sub-procedures, including information extraction and human-like design flow using Electronic Design Automation (EDA) tools. Besides, we also use a search method to mitigate the variation in code generation. Experimental results show that our method can significantly improve the functional correctness of the generated V erilog and reduce the hallucination of LLMs. As Moore's Law slowing down, there is an increasing demand for customized VLSI design. One of the key steps in the hardware design process is writing the hardware description language (HDL) code. However, HDL programming is time-consuming and labor-intensive. Therefore, the automatic HDL code generation from the specifications in natural language has attracted much attention in recent years. Among the automatic HDL code generation solutions, large language models (LLMs) code generation is one of the most promising solutions. LLMs have achieved remarkable success in various fields, such as machine translation [1] and robot trajectory planning [2]. In software design, LLMs have also demonstrated the ability to generate the code for various programming languages [3]. In the field of hardware design, generative models have been employed to create designs [4].

Large language models (LLMs) have demonstrated strong potential in performing automatic scoring for constructed response assessments. While constructed responses graded by humans are usually based on given grading rubrics, the methods by which LLMs assign scores remain largely unclear. It is also uncertain how closely AI's scoring process mirrors that of humans, or if it adheres to the same grading criteria. To address this gap, this paper uncovers the grading rubrics that LLMs used to score students' written responses to science tasks and their alignment with human scores. We also examine whether enhancing the alignments can improve scoring accuracy. Specifically, we prompt LLMs to generate analytic rubrics that they use to assign scores and study the alignment gap with human grading rubrics. Based on a series of experiments with various configurations of LLM settings, we reveal a notable alignment gap between human and LLM graders. While LLMs can adapt quickly to scoring tasks, they often resort to shortcuts, bypassing deeper logical reasoning expected in human grading. We found that incorporating high-quality analytical rubrics designed to reflect human grading logic can mitigate this gap and enhance LLMs' scoring accuracy. These results caution against the simplistic application of LLMs in science education and highlight the importance of aligning LLM outputs with human expectations to ensure efficient and accurate automatic scoring.

In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper introduces MELODI - Monitoring Energy Levels and Optimization for Data-driven Inference - a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of a comprehensive dataset reflective of energy efficiency across varied deployment scenarios. The dataset, generated using MELODI, encompasses a broad spectrum of LLM deployment frameworks, multiple language models, and extensive prompt datasets, enabling a comparative analysis of energy use. Using the dataset, we investigate how prompt attributes, including length and complexity, correlate with energy expenditure. Our findings indicate substantial disparities in energy efficiency, suggesting ample scope for optimization and adoption of sustainable measures in LLM deployment. Our contribution lies not only in the MELODI framework but also in the novel dataset, a resource that can be expanded by other researchers. Thus, MELODI is a foundational tool and dataset for advancing research into energy-conscious LLM deployment, steering the field toward a more sustainable future.

Large Language Models (LLMs) vary in their abilities on a range of tasks. Initiatives such as the $\texttt{Open LLM Leaderboard}$ aim to quantify these differences with several large benchmarks (sets of test items to which an LLM can respond either correctly or incorrectly). However, high correlations within and between benchmark scores suggest that (1) there exists a small set of common underlying abilities that these benchmarks measure, and (2) items tap into redundant information and the benchmarks may thus be considerably compressed. We use data from $n > 5000$ LLMs to identify the most informative items of six benchmarks, ARC, GSM8K, HellaSwag, MMLU, TruthfulQA and WinoGrande (with $d=28,632$ items in total). From them we distill a sparse benchmark, $\texttt{metabench}$, that has less than $3\%$ of the original size of all six benchmarks combined. This new sparse benchmark goes beyond point scores by yielding estimators of the underlying benchmark-specific abilities. We show that these estimators (1) can be used to reconstruct each original $\textit{individual}$ benchmark score with, on average, $1.5\%$ root mean square error (RMSE), (2) reconstruct the original $\textit{total}$ score with $0.8\%$ RMSE, and (3) have a single underlying common factor whose Spearman correlation with the total score is $r = 0.93$.

Accurate nutrition estimation helps people make informed decisions about their dietary choices and is crucial for preventing serious health issues. We present NutriBench, the first publicly available natural language meal description based nutrition benchmark. NutriBench consists of 5,000 human-verified meal descriptions with macro-nutrient labels, including carbohydrates, proteins, fats, and calories. The data is divided into 15 subsets varying in complexity based on the number, servings, and popularity of the food items in the meal and the specificity of serving size descriptions. We conducted an extensive evaluation of seven popular and state-of-the-art Large Language Models (LLMs), including GPT-3.5, Llama-3, and a medical domain-specific model with standard, Chain-of-Thought and Retrieval-Augmented Generation strategies on our benchmark for carbohydrate estimation. We also conducted a human study involving expert and non-expert participants and found that LLMs can provide more accurate and faster predictions over a range of complex queries. We present a thorough analysis and comparison of different LLMs, highlighting the opportunities and challenges of using LLMs for nutrition estimation in real-life scenarios. Our benchmark is publicly available at: https://mehak126.github.io/nutribench.html