Multimodal Reranking for Knowledge-Intensive Visual Question Answering

Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking quality of knowledge candidates for answer generation. Our reranking module takes multi-modal information from both candidates and questions and performs cross-item interaction for better relevance score modeling. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements. We also find a training-testing discrepancy with reranking in answer generation, where performance improves if training knowledge candidates are similar to or noisier than those used in testing.

Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I

The traditional evaluation of information retrieval (IR) systems is generally very costly as it requires manual relevance annotation from human experts. Recent advancements in generative artificial intelligence -- specifically large language models (LLMs) -- can generate relevance annotations at an enormous scale with relatively small computational costs. Potentially, this could alleviate the costs traditionally associated with IR evaluation and make it applicable to numerous low-resource applications. However, generated relevance annotations are not immune to (systematic) errors, and as a result, directly using them for evaluation produces unreliable results. In this work, we propose two methods based on prediction-powered inference and conformal risk control that utilize computer-generated relevance annotations to place reliable confidence intervals (CIs) around IR evaluation metrics. Our proposed methods require a small number of reliable annotations from which the methods can statistically analyze the errors in the generated annotations. Using this information, we can place CIs around evaluation metrics with strong theoretical guarantees. Unlike existing approaches, our conformal risk control method is specifically designed for ranking metrics and can vary its CIs per query and document. Our experimental results show that our CIs accurately capture both the variance and bias in evaluation based on LLM annotations, better than the typical empirical bootstrapping estimates. We hope our contributions bring reliable evaluation to the many IR applications where this was traditionally infeasible.

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs

Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings. Knowledge distillation (KD) offers a viable solution by transferring expertise from large teacher models to compact student models. However, traditional KD techniques face specific challenges when applied to LLMs, including restricted access to LLM outputs, significant teacher-student capacity gaps, and the inherited mis-calibration issue. In this work, we present PLaD, a novel preference-based LLM distillation framework. PLaD exploits the teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. Then, PLaD leverages a ranking loss to re-calibrate student's estimation of sequence likelihood, which steers the student's focus towards understanding the relative quality of outputs instead of simply imitating the teacher. PLaD bypasses the need for access to teacher LLM's internal states, tackles the student's expressivity limitations, and mitigates the student mis-calibration issue. Through extensive experiments on two sequence generation tasks and with various LLMs, we demonstrate the effectiveness of our proposed PLaD framework.

Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization

This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of marginalization and document independence, made in most prior work. Stochastic RAG casts the retrieval process in RAG as a stochastic sampling without replacement process. Through this formulation, we employ straight-through Gumbel-top-k that provides a differentiable approximation for sampling without replacement and enables effective end-to-end optimization for RAG. We conduct extensive experiments on seven diverse datasets on a wide range of tasks, from open-domain question answering to fact verification to slot-filling for relation extraction and to dialogue systems. By applying this optimization method to a recent and effective RAG model, we advance state-of-the-art results on six out of seven datasets.

Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing

The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly asking about relevancy, such as ``How relevant is document A to query Q?", results in sub-optimal ranking. Instead, the pairwise ranking prompting (PRP) approach produces promising ranking performance through asking about pairwise comparisons, e.g., ``Is document A more relevant than document B to query Q?". Thus, while LLMs are effective at their ranking ability, this is not reflected in their relevance label generation. In this work, we propose a post-processing method to consolidate the relevance labels generated by an LLM with its powerful ranking abilities. Our method takes both LLM generated relevance labels and pairwise preferences. The labels are then altered to satisfy the pairwise preferences of the LLM, while staying as close to the original values as possible. Our experimental results indicate that our approach effectively balances label accuracy and ranking performance. Thereby, our work shows it is possible to combine both the ranking and labeling abilities of LLMs through post-processing.

Unlocking the `Why' of Buying: Introducing a New Dataset and Benchmark for Purchase Reason and Post-Purchase Experience

Explanations are crucial for enhancing user trust and understanding within modern recommendation systems. To build truly explainable systems, we need high-quality datasets that elucidate why users make choices. While previous efforts have focused on extracting users' post-purchase sentiment in reviews, they ignore the reasons behind the decision to buy. In our work, we propose a novel purchase reason explanation task. To this end, we introduce an LLM-based approach to generate a dataset that consists of textual explanations of why real users make certain purchase decisions. We induce LLMs to explicitly distinguish between the reasons behind purchasing a product and the experience after the purchase in a user review. An automated, LLM-driven evaluation, as well as a small scale human evaluation, confirms the effectiveness of our approach to obtaining high-quality, personalized explanations. We benchmark this dataset on two personalized explanation generation tasks. We release the code and prompts to spur further research.

PRewrite: Prompt Rewriting with Reinforcement Learning

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion. This manual procedure can be time consuming, ineffective, and the generated prompts are, in a lot of cases, sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications? To address these questions, in this paper, we investigate prompt engineering automation. We consider a specific use case scenario in which developers/users have drafted initial prompts, but lack the time/expertise to optimize them. We propose PRewrite, an automated tool to rewrite these drafts and to generate highly effective new prompts. PRewrite is based on the Reinforcement Learning (RL) framework which allows for end-to-end optimization and our design allows the RL search to happen in a large action space. The automated tool leverages manually crafted prompts as starting points which makes the rewriting procedure more guided and efficient. The generated prompts are human readable, and self-explanatory, unlike some of those in previous works. We conducted extensive experiments on diverse datasets and found that the prompts generated with this new method not only outperform professionally crafted prompts, but also prompts generated with other previously proposed methods.

Bridging the Preference Gap between Retrievers and LLMs

Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, while retrieval has long been established as an effective means of obtaining task-relevant information for humans. Retrieval-augmented Generation (RAG) are known for their effectiveness in knowledge-intensive tasks by locating relevant information and placing it within the context window of the LLM. However, the relationship between retrievers and LLMs is still under-investigated. Most existing work treats the retriever and the LLM as independent components and leaves a gap between retrieving human-friendly information and assembling a LLM-friendly context. In this work, we examine a novel bridge model, validate the ranking and selection assumptions in retrievers in the context of RAG, and propose a training framework that chains together supervised and reinforcement learning to learn a bridge model. Empirical results demonstrate the effectiveness of our method in both question-answering and personalized generation tasks.

Creator Context for Tweet Recommendation

When discussing a tweet, people usually not only refer to the content it delivers, but also to the person behind the tweet. In other words, grounding the interpretation of the tweet in the context of its creator plays an important role in deciphering the true intent and the importance of the tweet. In this paper, we attempt to answer the question of how creator context should be used to advance tweet understanding. Specifically, we investigate the usefulness of different types of creator context, and examine different model structures for incorporating creator context in tweet modeling. We evaluate our tweet understanding models on a practical use case -- recommending relevant tweets to news articles. This use case already exists in popular news apps, and can also serve as a useful assistive tool for journalists. We discover that creator context is essential for tweet understanding, and can improve application metrics by a large margin. However, we also observe that not all creator contexts are equal. Creator context can be time sensitive and noisy. Careful creator context selection and deliberate model structure design play an important role in creator context effectiveness.

Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning

In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs). Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies have shown that using LLMs' outputs as labels is effective in training models to select demonstrations. Such a label is expected to estimate utility of a demonstration in ICL; however, it has not been well understood how different labeling strategies affect results on target tasks. This paper presents an analysis on different utility functions by focusing on LLMs' output probability given ground-truth output, and task-specific reward given LLMs' prediction. Unlike the previous work, we introduce a novel labeling method, incremental utility, which estimates how much incremental knowledge is brought into the LLMs by a demonstration. We conduct experiments with instruction-tuned LLMs on binary/multi-class classification, segmentation, and translation across Arabic, English, Finnish, Japanese, and Spanish. Our results show that (1) the probability is effective when the probability values are distributed across the whole value range (on the classification tasks), and (2) the downstream metric is more robust when nuanced reward values are provided with long outputs (on the segmentation and translation tasks). We then show that the proposed incremental utility further helps ICL by contrasting how the LLMs perform with and without the demonstrations.