Tomer Wolfson

Ori Yoran, Tomer Wolfson, Ori Ram et al. · deepmind

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance when it is relevant, and does not harm performance when it is not. This is particularly important in multi-hop reasoning scenarios, where misuse of irrelevant evidence can lead to cascading errors. However, recent work has shown that retrieval augmentation can sometimes have a negative effect on performance. In this work, we present a thorough analysis on five open-domain question answering benchmarks, characterizing cases when retrieval reduces accuracy. We then propose two methods to mitigate this issue. First, a simple baseline that filters out retrieved passages that do not entail question-answer pairs according to a natural language inference (NLI) model. This is effective in preventing performance reduction, but at a cost of also discarding relevant passages. Thus, we propose a method for automatically generating data to fine-tune the language model to properly leverage retrieved passages, using a mix of relevant and irrelevant contexts at training time. We empirically show that even 1,000 examples suffice to train the model to be robust to irrelevant contexts while maintaining high performance on examples with relevant ones.

Ori Yoran, Tomer Wolfson, Ben Bogin et al. · deepmind

Modern systems for multi-hop question answering (QA) typically break questions into a sequence of reasoning steps, termed chain-of-thought (CoT), before arriving at a final answer. Often, multiple chains are sampled and aggregated through a voting mechanism over the final answers, but the intermediate steps themselves are discarded. While such approaches improve performance, they do not consider the relations between intermediate steps across chains and do not provide a unified explanation for the predicted answer. We introduce Multi-Chain Reasoning (MCR), an approach which prompts large language models to meta-reason over multiple chains of thought, rather than aggregating their answers. MCR examines different reasoning chains, mixes information between them and selects the most relevant facts in generating an explanation and predicting the answer. MCR outperforms strong baselines on 7 multi-hop QA datasets. Moreover, our analysis reveals that MCR explanations exhibit high quality, enabling humans to verify its answers.

Samuel Joseph Amouyal, Tomer Wolfson, Ohad Rubin et al. · deepmind

Existing benchmarks for open-domain question answering (ODQA) typically focus on questions whose answers can be extracted from a single paragraph. By contrast, many natural questions, such as "What players were drafted by the Brooklyn Nets?" have a list of answers. Answering such questions requires retrieving and reading from many passages, in a large corpus. We introduce QAMPARI, an ODQA benchmark, where question answers are lists of entities, spread across many paragraphs. We created QAMPARI by (a) generating questions with multiple answers from Wikipedia's knowledge graph and tables, (b) automatically pairing answers with supporting evidence in Wikipedia paragraphs, and (c) manually paraphrasing questions and validating each answer. We train ODQA models from the retrieve-and-read family and find that QAMPARI is challenging in terms of both passage retrieval and answer generation, reaching an F1 score of 32.8 at best. Our results highlight the need for developing ODQA models that handle a broad range of question types, including single and multi-answer questions.

Dhruv Madhwal, Lyuxin David Zhang, Dan Roth et al.

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks. We find that although accuracy gains from decomposition diminish in frontier models, disagreements between prompting regimes remain highly indicative of potential errors. Because factual knowledge is stable while hallucinations are stochastic, cross-regime agreement provides a precise signal of internal uncertainty. We leverage this signal to implement a training-free abstention policy that requires no retrieval or fine-tuning. Our results show that disagreement-based abstention outperforms standard uncertainty baselines as an error detector, improving both F1 and AUROC across settings. This demonstrates that decomposition-based prompting can serve as a practical diagnostic probe for model reliability in closed-book QA.

Yevgeni Berkovitch, Oren Glickman, Amit Somech et al.

We explore generating factual and accurate tables from the parametric knowledge of large language models (LLMs). While LLMs have demonstrated impressive capabilities in recreating knowledge bases and generating free-form text, we focus on generating structured tabular data, which is crucial in domains like finance and healthcare. We examine the table generation abilities of four state-of-the-art LLMs: GPT-3.5, GPT-4, Llama2-13B, and Llama2-70B, using three prompting methods for table generation: (a) full-table, (b) row-by-row; (c) cell-by-cell. For evaluation, we introduce a novel benchmark, WikiTabGen which contains 100 curated Wikipedia tables. Tables are further processed to ensure their factual correctness and manually annotated with short natural language descriptions. Our findings reveal that table generation remains a challenge, with GPT-4 reaching the highest accuracy at 19.6%. Our detailed analysis sheds light on how various table properties, such as size, table popularity, and numerical content, influence generation performance. This work highlights the unique challenges in LLM-based table generation and provides a solid evaluation framework for future research. Our code, prompts and data are all publicly available: https://github.com/analysis-bots/WikiTabGen

Tomer Wolfson, Harsh Trivedi, Mor Geva et al. · deepmind

Automated agents, powered by Large language models (LLMs), are emerging as the go-to tool for querying information. However, evaluation benchmarks for LLM agents rarely feature natural questions that are both information-seeking and genuinely time-consuming for humans. To address this gap we introduce MoNaCo, a benchmark of 1,315 natural and time-consuming questions that require dozens, and at times hundreds, of intermediate steps to solve -- far more than any existing QA benchmark. To build MoNaCo, we developed a decomposed annotation pipeline to elicit and manually answer real-world time-consuming questions at scale. Frontier LLMs evaluated on MoNaCo achieve at most 61.2% F1, hampered by low recall and hallucinations. Our results underscore the limitations of LLM-powered agents in handling the complexity and sheer breadth of real-world information-seeking tasks -- with MoNaCo providing an effective resource for tracking such progress. The MoNaCo benchmark, codebase, prompts and models predictions are all publicly available at: https://tomerwolgithub.github.io/monaco

Peter Baile Chen, Tomer Wolfson, Michael Cafarella et al.

Existing information retrieval systems excel in cases where the language of target documents closely matches that of the user query. However, real-world retrieval systems are often required to implicitly reason whether a document is relevant. For example, when retrieving technical texts or tables, their relevance to the user query may be implied through a particular jargon or structure, rather than explicitly expressed in their content. Large language models (LLMs) hold great potential in identifying such implied relevance by leveraging their reasoning skills. Nevertheless, current LLM-augmented retrieval is hindered by high latency and computation cost, as the LLM typically computes the query-document relevance online, for every query anew. To tackle this issue we introduce EnrichIndex, a retrieval approach which instead uses the LLM offline to build semantically-enriched retrieval indices, by performing a single pass over all documents in the retrieval corpus once during ingestion time. Furthermore, the semantically-enriched indices can complement existing online retrieval approaches, boosting the performance of LLM re-rankers. We evaluated EnrichIndex on five retrieval tasks, involving passages and tables, and found that it outperforms strong online LLM-based retrieval systems, with an average improvement of 11.7 points in recall @ 10 and 10.6 points in NDCG @ 10 compared to strong baselines. In terms of online calls to the LLM, it processes 293.3 times fewer tokens which greatly reduces the online latency and cost. Overall, EnrichIndex is an effective way to build better retrieval indices offline by leveraging the strong reasoning skills of LLMs.

Tomer Wolfson, Daniel Deutch, Jonathan Berant

Text-to-SQL parsers are crucial in enabling non-experts to effortlessly query relational data. Training such parsers, by contrast, generally requires expertise in annotating natural language (NL) utterances with corresponding SQL queries. In this work, we propose a weak supervision approach for training text-to-SQL parsers. We take advantage of the recently proposed question meaning representation called QDMR, an intermediate between NL and formal query languages. Given questions, their QDMR structures (annotated by non-experts or automatically predicted), and the answers, we are able to automatically synthesize SQL queries that are used to train text-to-SQL models. We test our approach by experimenting on five benchmark datasets. Our results show that the weakly supervised models perform competitively with those trained on annotated NL-SQL data. Overall, we effectively train text-to-SQL parsers, while using zero SQL annotations.

Mor Geva, Tomer Wolfson, Jonathan Berant

Recent efforts to create challenge benchmarks that test the abilities of natural language understanding models have largely depended on human annotations. In this work, we introduce the "Break, Perturb, Build" (BPB) framework for automatic reasoning-oriented perturbation of question-answer pairs. BPB represents a question by decomposing it into the reasoning steps that are required to answer it, symbolically perturbs the decomposition, and then generates new question-answer pairs. We demonstrate the effectiveness of BPB by creating evaluation sets for three reading comprehension (RC) benchmarks, generating thousands of high-quality examples without human intervention. We evaluate a range of RC models on our evaluation sets, which reveals large performance gaps on generated examples compared to the original data. Moreover, symbolic perturbations enable fine-grained analysis of the strengths and limitations of models. Last, augmenting the training data with examples generated by BPB helps close the performance gaps, without any drop on the original data distribution.

Sanjay Subramanian, Ben Bogin, Nitish Gupta et al.

Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network architecture. However, prior work implicitly assumed that the structure of the network modules, describing the abstract reasoning process, provides a faithful explanation of the model's reasoning; that is, that all modules perform their intended behaviour. In this work, we propose and conduct a systematic evaluation of the intermediate outputs of NMNs on NLVR2 and DROP, two datasets which require composing multiple reasoning steps. We find that the intermediate outputs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour. To remedy that, we train the model with auxiliary supervision and propose particular choices for module architecture that yield much better faithfulness, at a minimal cost to accuracy.

Tomer Wolfson, Mor Geva, Ankit Gupta et al.

Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through natural language, that are necessary for answering a question. We develop a crowdsourcing pipeline, showing that quality QDMRs can be annotated at scale, and release the Break dataset, containing over 83K pairs of questions and their QDMRs. We demonstrate the utility of QDMR by showing that (a) it can be used to improve open-domain question answering on the HotpotQA dataset, (b) it can be deterministically converted to a pseudo-SQL formal language, which can alleviate annotation in semantic parsing applications. Last, we use Break to train a sequence-to-sequence model with copying that parses questions into QDMR structures, and show that it substantially outperforms several natural baselines.

Jonathan Berant, Daniel Deutch, Amir Globerson et al.

Designing a reliable natural language (NL) interface for querying tables has been a longtime goal of researchers in both the data management and natural language processing (NLP) communities. Such an interface receives as input an NL question, translates it into a formal query, executes the query and returns the results. Errors in the translation process are not uncommon, and users typically struggle to understand whether their query has been mapped correctly. We address this problem by explaining the obtained formal queries to non-expert users. Two methods for query explanations are presented: the first translates queries into NL, while the second method provides a graphic representation of the query cell-based provenance (in its execution on a given table). Our solution augments a state-of-the-art NL interface over web tables, enhancing it in both its training and deployment phase. Experiments, including a user study conducted on Amazon Mechanical Turk, show our solution to improve both the correctness and reliability of an NL interface.