Massimiliano Ciaramita

Bernd Bohnet, Vinh Q. Tran, Pat Verga et al. · deepmind, mit

Large language models (LLMs) have shown impressive results while requiring little or no direct supervision. Further, there is mounting evidence that LLMs may have potential in information-seeking scenarios. We believe the ability of an LLM to attribute the text that it generates is likely to be crucial in this setting. We formulate and study Attributed QA as a key first step in the development of attributed LLMs. We propose a reproducible evaluation framework for the task and benchmark a broad set of architectures. We take human annotations as a gold standard and show that a correlated automatic metric is suitable for development. Our experimental work gives concrete answers to two key questions (How to measure attribution?, and How well do current state-of-the-art methods perform on attribution?), and give some hints as to how to address a third (How to build LLMs with attribution?).

Leonard Adolphs, Michelle Chen Huebscher, Christian Buck et al. · eth-zurich

Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial to connect a query change to a change in the latent space that ultimately determines the retrieval results. To shed light on this embedding space, we learn a "query decoder" that, given a latent representation of a neural search engine, generates the corresponding query. We show that it is possible to decode a meaningful query from its latent representation and, when moving in the right direction in latent space, to decode a query that retrieves the relevant paragraph. In particular, the query decoder can be useful to understand "what should have been asked" to retrieve a particular paragraph from the collection. We employ the query decoder to generate a large synthetic dataset of query reformulations for MSMarco, leading to improved retrieval performance. On this data, we train a pseudo-relevance feedback (PRF) T5 model for the application of query suggestion that outperforms both query reformulation and PRF information retrieval baselines.

Jannis Bulian, Mike S. Schäfer, Afra Amini et al.

As Large Language Models (LLMs) rise in popularity, it is necessary to assess their capability in critically relevant domains. We present a comprehensive evaluation framework, grounded in science communication research, to assess LLM responses to questions about climate change. Our framework emphasizes both presentational and epistemological adequacy, offering a fine-grained analysis of LLM generations spanning 8 dimensions and 30 issues. Our evaluation task is a real-world example of a growing number of challenging problems where AI can complement and lift human performance. We introduce a novel protocol for scalable oversight that relies on AI Assistance and raters with relevant education. We evaluate several recent LLMs on a set of diverse climate questions. Our results point to a significant gap between surface and epistemological qualities of LLMs in the realm of climate communication.

Christian Buck, Levke Caesar, Michelle Chen Huebscher et al.

The emerging paradigm of AI co-scientists focuses on tasks characterized by repeatable verification, where agents explore search spaces in 'guess and check' loops. This paradigm does not extend to problems where repeated evaluation is impossible and ground truth is established by the consensus synthesis of theory and existing evidence. We evaluate a Gemini-based AI environment designed to support collaborative scientific assessment, integrated into a standard scientific workflow. In collaboration with a diverse group of 13 scientists working in the field of climate science, we tested the system on a complex topic: the stability of the Atlantic Meridional Overturning Circulation (AMOC). Our results show that AI can accelerate the scientific workflow. The group produced a comprehensive synthesis of 79 papers through 104 revision cycles in just over 46 person-hours. AI contribution was significant: most AI-generated content was retained in the report. AI also helped maintain logical consistency and presentation quality. However, expert additions were crucial to ensure its acceptability: less than half of the report was produced by AI. Furthermore, substantial oversight was required to expand and elevate the content to rigorous scientific standards.

Michelle Chen Huebscher, Christian Buck, Massimiliano Ciaramita et al.

Learning to search is the task of building artificial agents that learn to autonomously use a search box to find information. So far, it has been shown that current language models can learn symbolic query reformulation policies, in combination with traditional term-based retrieval, but fall short of outperforming neural retrievers. We extend the previous learning to search setup to a hybrid environment, which accepts discrete query refinement operations, after a first-pass retrieval step via a dual encoder. Experiments on the BEIR task show that search agents, trained via behavioral cloning, outperform the underlying search system based on a combined dual encoder retriever and cross encoder reranker. Furthermore, we find that simple heuristic Hybrid Retrieval Environments (HRE) can improve baseline performance by several nDCG points. The search agent based on HRE (HARE) matches state-of-the-art performance, balanced in both zero-shot and in-domain evaluations, via interpretable actions, and at twice the speed.

Michelle Chen Huebscher, Katharine Mach, Aleksandar Stanić et al.

Evaluating how Large Language Models (LLMs) handle complex, specialized knowledge remains a critical challenge. We address this through the lens of climate change by introducing CLINB, a benchmark that assesses models on open-ended, grounded, multimodal question answering tasks with clear requirements for knowledge quality and evidential support. CLINB relies on a dataset of real users' questions and evaluation rubrics curated by leading climate scientists. We implement and validate a model-based evaluation process and evaluate several frontier models. Our findings reveal a critical dichotomy. Frontier models demonstrate remarkable knowledge synthesis capabilities, often exhibiting PhD-level understanding and presentation quality. They outperform "hybrid" answers curated by domain experts assisted by weaker models. However, this performance is countered by failures in grounding. The quality of evidence varies, with substantial hallucination rates for references and images. We argue that bridging this gap between knowledge synthesis and verifiable attribution is essential for the deployment of AI in scientific workflows and that reliable, interpretable benchmarks like CLINB are needed to progress towards building trustworthy AI systems.

Afra Amini, Massimiliano Ciaramita

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on the instruction. Importantly, such dependency on the context can surface in unpredictable ways, e.g., a seemingly more informative instruction might lead to a worse performance. In this paper, we propose an alternative approach, which we term In-Context Probing (ICP). Similar to in-context learning, we contextualize the representation of the input with an instruction, but instead of decoding the output prediction, we probe the contextualized representation to predict the label. Through a series of experiments on a diverse set of classification tasks, we show that in-context probing is significantly more robust to changes in instructions. We further show that ICP performs competitive or superior to finetuning and can be particularly helpful to build classifiers on top of smaller models, with less than a hundred training examples.

Leonard Adolphs, Benjamin Boerschinger, Christian Buck et al.

This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from aggregated search results. Agents are then empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results. We develop a novel way of generating synthetic search sessions, which leverages the power of transformer-based language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that learns interactive search strategies from scratch. Our search agents obtain retrieval and answer quality performance comparable to recent neural methods, using only a traditional term-based BM25 ranking function and interpretable discrete reranking and filtering actions.

Thomas Diggelmann, Jordan Boyd-Graber, Jannis Bulian et al.

We introduce CLIMATE-FEVER, a new publicly available dataset for verification of climate change-related claims. By providing a dataset for the research community, we aim to facilitate and encourage work on improving algorithms for retrieving evidential support for climate-specific claims, addressing the underlying language understanding challenges, and ultimately help alleviate the impact of misinformation on climate change. We adapt the methodology of FEVER [1], the largest dataset of artificially designed claims, to real-life claims collected from the Internet. While during this process, we could rely on the expertise of renowned climate scientists, it turned out to be no easy task. We discuss the surprising, subtle complexity of modeling real-world climate-related claims within the \textsc{fever} framework, which we believe provides a valuable challenge for general natural language understanding. We hope that our work will mark the beginning of a new exciting long-term joint effort by the climate science and AI community.

Francesco S. Varini, Jordan Boyd-Graber, Massimiliano Ciaramita et al.

Climate change communication in the mass media and other textual sources may affect and shape public perception. Extracting climate change information from these sources is an important task, e.g., for filtering content and e-discovery, sentiment analysis, automatic summarization, question-answering, and fact-checking. However, automating this process is a challenge, as climate change is a complex, fast-moving, and often ambiguous topic with scarce resources for popular text-based AI tasks. In this paper, we introduce \textsc{ClimaText}, a dataset for sentence-based climate change topic detection, which we make publicly available. We explore different approaches to identify the climate change topic in various text sources. We find that popular keyword-based models are not adequate for such a complex and evolving task. Context-based algorithms like BERT \cite{devlin2018bert} can detect, in addition to many trivial cases, a variety of complex and implicit topic patterns. Nevertheless, our analysis reveals a great potential for improvement in several directions, such as, e.g., capturing the discussion on indirect effects of climate change. Hence, we hope this work can serve as a good starting point for further research on this topic.

Benjamin Borschinger, Jordan Boyd-Graber, Christian Buck et al.

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. The environment encapsulates a competitive machine reader based on BERT, providing candidate answers to questions, and possibly some context. To validate the realism of our formulation, we ask humans to play the role of a meta-answerer. With just a small snippet of text around an answer, humans can outperform the machine reader, improving recall. Similarly, a simple machine meta-answerer outperforms the environment, improving both precision and recall on the Natural Questions dataset. The system relies on joint training of answer scoring and the selection of conditioning information.

Gino Brunner, Yang Liu, Damián Pascual et al.

In this paper we delve deep in the Transformer architecture by investigating two of its core components: self-attention and contextual embeddings. In particular, we study the identifiability of attention weights and token embeddings, and the aggregation of context into hidden tokens. We show that, for sequences longer than the attention head dimension, attention weights are not identifiable. We propose effective attention as a complementary tool for improving explanatory interpretations based on attention. Furthermore, we show that input tokens retain to a large degree their identity across the model. We also find evidence suggesting that identity information is mainly encoded in the angle of the embeddings and gradually decreases with depth. Finally, we demonstrate strong mixing of input information in the generation of contextual embeddings by means of a novel quantification method based on gradient attribution. Overall, we show that self-attention distributions are not directly interpretable and present tools to better understand and further investigate Transformer models.

Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer. Sub-agents are trained on disjoint partitions of the training data, while the meta-agent is trained on the full training set. Our method makes learning faster, because it is highly parallelizable, and has better generalization performance than strong baselines, such as an ensemble of agents trained on the full data. We show that the improved performance is due to the increased diversity of reformulation strategies.

Lierni Sestorain, Massimiliano Ciaramita, Christian Buck et al.

Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines zero-shot and dual learning. The latter relies on reinforcement learning, to exploit the duality of the machine translation task, and requires only monolingual data for the target language pair. Experiments show that a zero-shot dual system, trained on English-French and English-Spanish, outperforms by large margins a standard NMT system in zero-shot translation performance on Spanish-French (both directions). The zero-shot dual method approaches the performance, within 2.2 BLEU points, of a comparable supervised setting. Our method can obtain improvements also on the setting where a small amount of parallel data for the zero-shot language pair is available. Adding Russian, to extend our experiments to jointly modeling 6 zero-shot translation directions, all directions improve between 4 and 15 BLEU points, again, reaching performance near that of the supervised setting.

Christian Buck, Jannis Bulian, Massimiliano Ciaramita et al.

We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017]. In ActiveQA, question answering is framed as a reinforcement learning task in which an agent sits between the user and a black box question-answering system. The agent learns to reformulate the user's questions to elicit the optimal answers. It probes the system with many versions of a question that are generated via a sequence-to-sequence question reformulation model, then aggregates the returned evidence to find the best answer. This process is an instance of \emph{machine-machine} communication. The question reformulation model must adapt its language to increase the quality of the answers returned, matching the language of the question answering system. We find that the agent does not learn transformations that align with semantic intuitions but discovers through learning classical information retrieval techniques such as tf-idf re-weighting and stemming.

Christian Buck, Jannis Bulian, Massimiliano Ciaramita et al.

We frame Question Answering (QA) as a Reinforcement Learning task, an approach that we call Active Question Answering. We propose an agent that sits between the user and a black box QA system and learns to reformulate questions to elicit the best possible answers. The agent probes the system with, potentially many, natural language reformulations of an initial question and aggregates the returned evidence to yield the best answer. The reformulation system is trained end-to-end to maximize answer quality using policy gradient. We evaluate on SearchQA, a dataset of complex questions extracted from Jeopardy!. The agent outperforms a state-of-the-art base model, playing the role of the environment, and other benchmarks. We also analyze the language that the agent has learned while interacting with the question answering system. We find that successful question reformulations look quite different from natural language paraphrases. The agent is able to discover non-trivial reformulation strategies that resemble classic information retrieval techniques such as term re-weighting (tf-idf) and stemming.

Neil Houlsby, Massimiliano Ciaramita

We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed inference and representation framework based on a parallel Gibbs sampler guided by the Wikipedia link graph, and pipelines of MapReduce allowing fast and memory-frugal processing of large datasets. We report state-of-the-art performance on a public dataset.