Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions

Conversational question-answering (CQA) systems aim to create interactive search systems that effectively retrieve information by interacting with users. To replicate human-to-human conversations, existing work uses human annotators to play the roles of the questioner (student) and the answerer (teacher). Despite its effectiveness, challenges exist as human annotation is time-consuming, inconsistent, and not scalable. To address this issue and investigate the applicability of large language models (LLMs) in CQA simulation, we propose a simulation framework that employs zero-shot learner LLMs for simulating teacher-student interactions. Our framework involves two LLMs interacting on a specific topic, with the first LLM acting as a student, generating questions to explore a given search topic. The second LLM plays the role of a teacher by answering questions and is equipped with additional information, including a text on the given topic. We implement both the student and teacher by zero-shot prompting the GPT-4 model. To assess the effectiveness of LLMs in simulating CQA interactions and understand the disparities between LLM- and human-generated conversations, we evaluate the simulated data from various perspectives. We begin by evaluating the teacher's performance through both automatic and human assessment. Next, we evaluate the performance of the student, analyzing and comparing the disparities between questions generated by the LLM and those generated by humans. Furthermore, we conduct extensive analyses to thoroughly examine the LLM performance by benchmarking state-of-the-art reading comprehension models on both datasets. Our results reveal that the teacher LLM generates lengthier answers that tend to be more accurate and complete. The student LLM generates more diverse questions, covering more aspects of a given topic.

Query Performance Prediction: From Ad-hoc to Conversational Search

Query performance prediction (QPP) is a core task in information retrieval. The QPP task is to predict the retrieval quality of a search system for a query without relevance judgments. Research has shown the effectiveness and usefulness of QPP for ad-hoc search. Recent years have witnessed considerable progress in conversational search (CS). Effective QPP could help a CS system to decide an appropriate action to be taken at the next turn. Despite its potential, QPP for CS has been little studied. We address this research gap by reproducing and studying the effectiveness of existing QPP methods in the context of CS. While the task of passage retrieval remains the same in the two settings, a user query in CS depends on the conversational history, introducing novel QPP challenges. In particular, we seek to explore to what extent findings from QPP methods for ad-hoc search generalize to three CS settings: (i) estimating the retrieval quality of different query rewriting-based retrieval methods, (ii) estimating the retrieval quality of a conversational dense retrieval method, and (iii) estimating the retrieval quality for top ranks vs. deeper-ranked lists. Our findings can be summarized as follows: (i) supervised QPP methods distinctly outperform unsupervised counterparts only when a large-scale training set is available; (ii) point-wise supervised QPP methods outperform their list-wise counterparts in most cases; and (iii) retrieval score-based unsupervised QPP methods show high effectiveness in assessing the conversational dense retrieval method, ConvDR.

Exploiting Simulated User Feedback for Conversational Search: Ranking, Rewriting, and Beyond

This research aims to explore various methods for assessing user feedback in mixed-initiative conversational search (CS) systems. While CS systems enjoy profuse advancements across multiple aspects, recent research fails to successfully incorporate feedback from the users. One of the main reasons for that is the lack of system-user conversational interaction data. To this end, we propose a user simulator-based framework for multi-turn interactions with a variety of mixed-initiative CS systems. Specifically, we develop a user simulator, dubbed ConvSim, that, once initialized with an information need description, is capable of providing feedback to a system's responses, as well as answering potential clarifying questions. Our experiments on a wide variety of state-of-the-art passage retrieval and neural re-ranking models show that effective utilization of user feedback can lead to 16% retrieval performance increase in terms of nDCG@3. Moreover, we observe consistent improvements as the number of feedback rounds increases (35% relative improvement in terms of nDCG@3 after three rounds). This points to a research gap in the development of specific feedback processing modules and opens a potential for significant advancements in CS. To support further research in the topic, we release over 30,000 transcripts of system-simulator interactions based on well-established CS datasets.

Generating Synthetic Documents for Cross-Encoder Re-Rankers: A Comparative Study of ChatGPT and Human Experts

We investigate the usefulness of generative Large Language Models (LLMs) in generating training data for cross-encoder re-rankers in a novel direction: generating synthetic documents instead of synthetic queries. We introduce a new dataset, ChatGPT-RetrievalQA, and compare the effectiveness of models fine-tuned on LLM-generated and human-generated data. Data generated with generative LLMs can be used to augment training data, especially in domains with smaller amounts of labeled data. We build ChatGPT-RetrievalQA based on an existing dataset, human ChatGPT Comparison Corpus (HC3), consisting of public question collections with human responses and answers from ChatGPT. We fine-tune a range of cross-encoder re-rankers on either human-generated or ChatGPT-generated data. Our evaluation on MS MARCO DEV, TREC DL'19, and TREC DL'20 demonstrates that cross-encoder re-ranking models trained on ChatGPT responses are statistically significantly more effective zero-shot re-rankers than those trained on human responses. In a supervised setting, the human-trained re-rankers outperform the LLM-trained re-rankers. Our novel findings suggest that generative LLMs have high potential in generating training data for neural retrieval models. Further work is needed to determine the effect of factually wrong information in the generated responses and test our findings' generalizability with open-source LLMs. We release our data, code, and cross-encoders checkpoints for future work.

On the Impact of Outlier Bias on User Clicks

User interaction data is an important source of supervision in counterfactual learning to rank (CLTR). Such data suffers from presentation bias. Much work in unbiased learning to rank (ULTR) focuses on position bias, i.e., items at higher ranks are more likely to be examined and clicked. Inter-item dependencies also influence examination probabilities, with outlier items in a ranking as an important example. Outliers are defined as items that observably deviate from the rest and therefore stand out in the ranking. In this paper, we identify and introduce the bias brought about by outlier items: users tend to click more on outlier items and their close neighbors. To this end, we first conduct a controlled experiment to study the effect of outliers on user clicks. Next, to examine whether the findings from our controlled experiment generalize to naturalistic situations, we explore real-world click logs from an e-commerce platform. We show that, in both scenarios, users tend to click significantly more on outlier items than on non-outlier items in the same rankings. We show that this tendency holds for all positions, i.e., for any specific position, an item receives more interactions when presented as an outlier as opposed to a non-outlier item. We conclude from our analysis that the effect of outliers on clicks is a type of bias that should be addressed in ULTR. We therefore propose an outlier-aware click model that accounts for both outlier and position bias, called outlier-aware position-based model ( OPBM). We estimate click propensities based on OPBM ; through extensive experiments performed on both real-world e-commerce data and semi-synthetic data, we verify the effectiveness of our outlier-aware click model. Our results show the superiority of OPBM against baselines in terms of ranking performance and true relevance estimation.

Market-Aware Models for Efficient Cross-Market Recommendation

We consider the cross-market recommendation (CMR) task, which involves recommendation in a low-resource target market using data from a richer, auxiliary source market. Prior work in CMR utilised meta-learning to improve recommendation performance in target markets; meta-learning however can be complex and resource intensive. In this paper, we propose market-aware (MA) models, which directly model a market via market embeddings instead of meta-learning across markets. These embeddings transform item representations into market-specific representations. Our experiments highlight the effectiveness and efficiency of MA models both in a pairwise setting with a single target-source market, as well as a global model trained on all markets in unison. In the former pairwise setting, MA models on average outperform market-unaware models in 85% of cases on nDCG@10, while being time-efficient - compared to meta-learning models, MA models require only 15% of the training time. In the global setting, MA models outperform market-unaware models consistently for some markets, while outperforming meta-learning-based methods for all but one market. We conclude that MA models are an efficient and effective alternative to meta-learning, especially in the global setting.

Experiments on Generalizability of BERTopic on Multi-Domain Short Text

Topic modeling is widely used for analytically evaluating large collections of textual data. One of the most popular topic techniques is Latent Dirichlet Allocation (LDA), which is flexible and adaptive, but not optimal for e.g. short texts from various domains. We explore how the state-of-the-art BERTopic algorithm performs on short multi-domain text and find that it generalizes better than LDA in terms of topic coherence and diversity. We further analyze the performance of the HDBSCAN clustering algorithm utilized by BERTopic and find that it classifies a majority of the documents as outliers. This crucial, yet overseen problem excludes too many documents from further analysis. When we replace HDBSCAN with k-Means, we achieve similar performance, but without outliers.

Towards Confidence-aware Calibrated Recommendation

Recommender systems utilize users' historical data to learn and predict their future interests, providing them with suggestions tailored to their tastes. Calibration ensures that the distribution of recommended item categories is consistent with the user's historical data. Mitigating miscalibration brings various benefits to a recommender system. For example, it becomes less likely that a system overlooks categories with less interaction on a user's profile by only recommending popular categories. Despite the notable success, calibration methods have several drawbacks, such as limiting the diversity of the recommended items and not considering the calibration confidence. This work, presents a set of properties that address various aspects of a desired calibrated recommender system. Considering these properties, we propose a confidence-aware optimization-based re-ranking algorithm to find the balance between calibration, relevance, and item diversity, while simultaneously accounting for calibration confidence based on user profile size. Our model outperforms state-of-the-art methods in terms of various accuracy and beyond-accuracy metrics for different user groups.