LLM-as-a-Judge, which uses LLMs to evaluate responses to open-ended questions, has seen significant growth in recent years. It has been adopted as a scalable alternative to manual human evaluation, such as crowdsourcing, which is often time-consuming and costly. However, the discrepancy between LLM-generated evaluations and human evaluations remains a critical problem in this field. To bridge this gap, we propose Multi-Aspect Panels of LLM Evaluators (MAPLE), a framework that orchestrates evaluations across multiple criteria using multiple LLMs. MAPLE integrates criterion-wise pairwise evaluations from multiple LLMs by estimating the importance of criteria and the reliability of individual evaluators. We conduct experiments with both open-source and closed-source models. Our results demonstrate that MAPLE achieves superior alignment with human evaluations compared to baselines, highlighting the importance of employing multi-agent and multi-criteria evaluation strategies.

Similarly to humans, LLMs are susceptible to the anchoring effect in price negotiations, which can lead to unfavorable or unintended outcomes. To ensure LLM safety in dialogue tasks such as negotiation, a mechanistic understanding and mitigation methods are essential. We propose four variants of a method to identify Anchoring Heads, which are the attention heads responsible for the anchoring effect, while preserving those essential for general tasks. Experimental results show that suppressing these heads mitigates the anchoring effect by over 16%, achieving complete mitigation in certain models without compromising general performance. Furthermore, the observation that suppressing random heads fails to mitigate the anchoring effect suggests that specific attention heads drive the anchoring effect by paying excessive attention to the anchor.

Formulating optimization problems from raw inputs of problem descriptions and data is time-consuming and costly. While Large Language Models (LLMs) offer a promising way to automate this process, existing benchmarks overestimate their capabilities by relying on idealized inputs where all data is relevant and complete. This diverges from reality, where data-centric reasoning is required to extract, compute, and predict parameters from noisy sources. To address this, we introduce NLData2Opt, a benchmark to evaluate LLMs on the multi-stage reasoning inherent in practical optimization workflows. NLData2Opt decomposes problems into problem descriptions and data, and requires models to (1) extract relevant parameters from data containing misleading attributes, (2) compute missing parameters derived by transforming existing data attributes, and (3) predict unavailable future values from historical observations. Evaluation results show substantial performance decline relative to existing benchmarks, indicating that benchmark progress does not directly translate to formulation accuracy in practical optimization workflows. NLData2Opt is available at https://github.com/sumarivyn/NLData2Opt.

This paper investigates defenses in LLM-based evaluation, where prompt injection attacks can manipulate scores by deceiving the evaluation system. We formalize blind attacks as a class in which candidate answers are crafted independently of the true answer. To counter such attacks, we propose an evaluation framework that combines standard and counterfactual evaluation. Experiments show it significantly improves attack detection with minimal performance trade-offs for recent models.

Deep learning models have performed well on many NLP tasks. However, their internal mechanisms are typically difficult for humans to understand. The development of methods to explain models has become a key issue in the reliability of deep learning models in many important applications. Various saliency explanation methods, which give each feature of input a score proportional to the contribution of output, have been proposed to determine the part of the input which a model values most. Despite a considerable body of work on the evaluation of saliency methods, whether the results of various evaluation metrics agree with human cognition remains an open question. In this study, we propose a new human-based method to evaluate saliency methods in NLP by crowdsourcing. We recruited 800 crowd workers and empirically evaluated seven saliency methods on two datasets with the proposed method. We analyzed the performance of saliency methods, compared our results with existing automated evaluation methods, and identified notable differences between NLP and computer vision (CV) fields when using saliency methods. The instance-level data of our crowdsourced experiments and the code to reproduce the explanations are available at https://github.com/xtlu/lreccoling_evaluation.

Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to open-ended questions. We utilized LLMs to generate multiple evaluation criteria for a question. Subsequently, answers were subjected to pairwise comparisons under each criterion with LLMs, and scores for each answer were calculated in the AHP. We conducted experiments on four datasets using both ChatGPT-3.5-turbo and GPT-4. Our results indicate that our approach more closely aligns with human judgment compared to the four baselines. Additionally, we explored the impact of the number of criteria, variations in models, and differences in datasets on the results.