Amir Taubenfeld
Research Areas
Authored Publications
Sort By
Confidence Improves Self-Consistency in LLMs
Tom Sheffer
Eran Ofek
Ariel Goldstein
Zorik Gekhman
ACL 2025, Findings (2025)
Preview abstract
Self-consistency decoding enhances LLMs’ performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally expensive, as sampling many of these (lengthy) paths is required to increase the chances that the correct answer emerges as the most frequent one. To address this, we introduce Confidence-Informed Self-Consistency (CISC). CISC performs a weighted majority vote based on confidence scores obtained directly from the model. By prioritizing high-confidence paths, it can identify the correct answer with a significantly smaller sample size. When tested on nine models and four datasets, CISC outperforms self-consistency in nearly all configurations, reducing the required number of reasoning paths by over 40% on average. In addition, we introduce the notion of within-question confidence evaluation, after showing that standard evaluation methods are poor predictors of success in distinguishing correct and incorrect answers to the same question. In fact, the most calibrated confidence method proved to be the least effective for CISC. Lastly, beyond these practical implications, our results and analyses show that LLMs can effectively judge the correctness of their own outputs, contributing to the ongoing debate on this topic.
View details
Preview abstract
The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly human-like in their performance, sparking interest in using these AI agents as substitutes for human participants in behavioral studies. However, LLMs are complex statistical learners without straightforward deductive rules, making them prone to unexpected behaviors. Hence, it is crucial to study and pinpoint the key behavioral distinctions between humans and LLM-based agents. In this study, we highlight the limitations of LLMs in simulating human interactions, particularly focusing on LLMs' ability to simulate political debates on topics that are important aspects of people's day-to-day lives and decision-making processes. Our findings indicate a tendency for LLM agents to conform to the model's inherent social biases despite being directed to debate from certain political perspectives. This tendency results in behavioral patterns that seem to deviate from well-established social dynamics among humans. We reinforce these observations using an automatic self-fine-tuning method, which enables us to manipulate the biases within the LLM and demonstrate that agents subsequently align with the altered biases. These results underscore the need for further research to develop methods that help agents overcome these biases, a critical step toward creating more realistic simulations.
View details
Building a Clinically-Focused Problem List From Medical Notes
Ayelet Benjamini
Birju Patel
Cathy Cheung
Hengrui Liu
Liwen Xu
Peter Clardy
Rachana Fellinger
LOUHI 2022: The 13th International Workshop on Health Text Mining and Information Analysis (2022)
Preview abstract
Clinical notes often contain vital information not observed in other structured data, but their unstructured nature can lead to critical patient-related information being lost. To make sure this valuable information is utilized for patient care, algorithms that summarize notes into a problem list are often proposed. Focusing on identifying medically-relevant entities in the free-form text, these solutions are often detached from a canonical ontology and do not allow downstream use of the detected text-spans. As a solution, we present here a system for generating a canonical problem list from medical notes, consisting of two major stages. At the first stage, annotation, we use a transformer model to detect all clinical conditions which are mentioned in a single note. These clinical conditions are then grounded to a predefined ontology, and are linked to spans in the text. At the second stage, summarization, we aggregate over the set of clinical conditions detected on all of the patient's note, and produce a concise patient summary that organizes their important conditions.
View details
