Related papers: Users as Annotators: LLM Preference Learning from …
Conversational recommendation frameworks have gained prominence as a dynamic paradigm for delivering personalized suggestions via interactive dialogues. The incorporation of advanced language understanding techniques has substantially…
Preference learning from pairwise feedback is a widely adopted framework in applications such as reinforcement learning with human feedback and recommendations. In many practical settings, however, user interactions are limited or costly,…
The output of large language models (LLMs) is unstable, due both to non-determinism of the decoding process as well as to prompt brittleness. While the intrinsic non-determinism of LLM generation may mimic existing uncertainty in human…
Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…
Although the annotation paradigm based on Large Language Models (LLMs) has made significant breakthroughs in recent years, its actual deployment still has two core bottlenecks: first, the cost of calling commercial APIs in large-scale…
Large Language Models (LLMs) have demonstrated exceptional capabilities in generalizing to new tasks in a zero-shot or few-shot manner. However, the extent to which LLMs can comprehend user preferences based on their previous behavior…
While Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, aligning these models with varying human preferences across multiple objectives remains a significant challenge…
Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…
Human coders are biased. We test similar biases in Large Language Models (LLMs) as annotators. By replicating an experiment run by Ennser-Jedenastik and Meyer (2018), we find evidence that LLMs use political information, and specifically…
The performance of pre-trained Large Language Models (LLMs) is often sensitive to nuances in prompt templates, requiring careful prompt engineering, adding costs in terms of computing and human effort. In this study, we present experiments…
Large Language Models (LLMs) like GPT-4o can help automate text classification tasks at low cost and scale. However, there are major concerns about the validity and reliability of LLM outputs. By contrast, human coding is generally more…
Recently, much effort has been devoted to modeling users' multi-interests based on their behaviors or auxiliary signals. However, existing methods often rely on heuristic assumptions, e.g., co-occurring items indicate the same interest of…
Can large language models (LLMs) learn a decision maker's preferences from observed choices and generate preference-consistent recommendations in new situations? We propose a portable Simulate-Recommend-Evaluate framework that tests…
Large language models (LLMs) must often respond to highly ambiguous user requests. In such cases, the LLM's best response may be to ask a clarifying question to elicit more information. Existing LLMs often respond by presupposing a single…
Serendipity-oriented recommender systems aim to counteract over-specialization in user preferences. However, evaluating a user's serendipitous response towards a recommended item can be challenging because of its emotional nature. In this…
Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing…
Supervised learning relies on high-quality labeled data, but obtaining such data through human annotation is both expensive and time-consuming. Recent work explores using large language models (LLMs) for annotation, but LLM-generated labels…
Recommender and search systems commonly rely on Learning To Rank models trained on logged user interactions to order items by predicted relevance. However, such interaction data is often subject to position bias, as users are more likely to…
Accurately modeling user preferences is vital not only for improving recommendation performance but also for enhancing transparency in recommender systems. Conventional user profiling methods, such as averaging item embeddings, often…
Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…