Knowledge Base Question Answering (KBQA) aims to answer natural language questions using structured knowledge from KBs. While LLM-only approaches offer generalization, they suffer from outdated knowledge, hallucinations, and lack of transparency. Chain-based KG-RAG methods address these issues by incorporating external KBs, but are limited to simple chain-structured questions due to the absence of planning and logical structuring. Inspired by semantic parsing methods, we propose PDRR: a four-stage framework consisting of Predict, Decompose, Retrieve, and Reason. Our method first predicts the question type and decomposes the question into structured triples. Then retrieves relevant information from KBs and guides the LLM as an agent to reason over and complete the decomposed triples. Experimental results demonstrate that PDRR consistently outperforms existing methods across various LLM backbones and achieves superior performance on both chain-structured and non-chain complex questions.

Properly evaluating the ability of Video-Language Models (VLMs) to understand long videos remains a challenge. We propose a long-context video understanding benchmark, Causal2Needles, that assesses two crucial abilities insufficiently addressed by existing benchmarks: (1) extracting information from two separate locations (two needles) in a long video and understanding them jointly, and (2) modeling the world in terms of cause and effect in human behaviors. Causal2Needles evaluates these abilities using noncausal one-needle, causal one-needle, and causal two-needle questions. The most complex question type, causal two-needle questions, require extracting information from both the cause and effect events from a long video and the associated narration text. To prevent textual bias, we introduce two complementary question formats: locating the video clip containing the answer, and verbal description of a visual detail from that video clip. Our experiments reveal that models excelling on existing benchmarks struggle with causal 2-needle questions, and the model performance is negatively correlated with the distance between the two needles. These findings highlight critical limitations in current VLMs. The dataset is available at: https://huggingface.co/datasets/causal2needles/Causal2Needles

Multi-Hop Question Answering (MHQA) is crucial for evaluating the model's capability to integrate information from diverse sources. However, creating extensive and high-quality MHQA datasets is challenging: (i) manual annotation is expensive, and (ii) current synthesis methods often produce simplistic questions or require extensive manual guidance. This paper introduces HopWeaver, the first cross-document framework synthesizing authentic multi-hop questions without human intervention. HopWeaver synthesizes bridge and comparison questions through an innovative pipeline that identifies complementary documents and constructs authentic reasoning paths to ensure true multi-hop reasoning. We further present a comprehensive system for evaluating the synthesized multi-hop questions. Empirical evaluations demonstrate that the synthesized questions achieve comparable or superior quality to human-annotated datasets at a lower cost. Our framework provides a valuable tool for the research community: it can automatically generate challenging benchmarks from any raw corpus, which opens new avenues for both evaluation and targeted training to improve the reasoning capabilities of advanced QA models, especially in domains with scarce resources.

Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought. We investigate this capability using GPT2-style language models trained from scratch on controlled $k$-hop reasoning datasets ($k = 2, 3, 4$). We show that while such models can indeed learn implicit $k$-hop reasoning, the required training data grows exponentially in $k$, and the required number of transformer layers grows linearly in $k$. We offer a theoretical explanation for why this depth growth is necessary. We further find that the data requirement can be mitigated, but not eliminated, through curriculum learning.

Evaluating Retrieval-Augmented Generation (RAG) in large language models (LLMs) is challenging because benchmarks can quickly become stale. Questions initially requiring retrieval may become answerable from pretraining knowledge as newer models incorporate more recent information during pretraining, making it difficult to distinguish evidence-based reasoning from recall. We introduce NeoQA (News Events for Out-of-training Question Answering), a benchmark designed to address this issue. To construct NeoQA, we generated timelines and knowledge bases of fictional news events and entities along with news articles and Q\&A pairs to prevent LLMs from leveraging pretraining knowledge, ensuring that no prior evidence exists in their training data. We propose our dataset as a new platform for evaluating evidence-based question answering, as it requires LLMs to generate responses exclusively from retrieved evidence and only when sufficient evidence is available. NeoQA enables controlled evaluation across various evidence scenarios, including cases with missing or misleading details. Our findings indicate that LLMs struggle to distinguish subtle mismatches between questions and evidence, and suffer from short-cut reasoning when key information required to answer a question is missing from the evidence, underscoring key limitations in evidence-based reasoning.

[Notice: This version is outdated. Recent research contradicts some key claims; we are working on a major revision with more nuanced analysis. Please wait for the updated version.] While LLMs excel at multi-hop questions (e.g. "Who is the spouse of the performer of Imagine?") when using chain-of-thought reasoning (CoT), they struggle when forced to reason internally (without CoT). Previous work on the size and nature of this gap produced mixed evidence with inconclusive results. In this paper, we introduce a controlled setting for investigating two-hop reasoning in LLMs, where the above-chance performance constitutes undeniable evidence for latent reasoning. We fine-tune LLMs (including Llama 3 8B Instruct and GPT-4o) on fictional facts and confirm that they generalize to answering two-hop questions about them using CoT. We find that models can perform latent reasoning when facts appear together during training or in the prompt. However, to our surprise, models completely fail at two-hop reasoning without CoT when learned facts only appear in different documents, achieving chance-level accuracy and chance-level test loss. We call this complete failure to compose separately learned facts the Two-Hop Curse. Moreover, we evaluate 9 frontier LLMs on real-world facts, finding that models completely fail at two-hop no-CoT reasoning for over half of question categories while maintaining partial success with CoT across most categories. These results suggest that LLMs lack a general capability for latent multi-hop reasoning independent of the question type.

We evaluate how well Large Language Models (LLMs) latently recall and compose facts to answer multi-hop queries like "In the year Scarlett Johansson was born, the Summer Olympics were hosted in the country of". One major challenge in evaluating this ability is that LLMs may have developed shortcuts by encounters of the head entity "Scarlett Johansson" and the answer entity "United States" in the same training sequences or merely guess the answer based on frequency-based priors. To prevent shortcuts, we exclude test queries where the head and answer entities co-appear in pretraining corpora. Through careful selection of relations and facts and systematic removal of cases where models might guess answers or exploit partial matches, we construct an evaluation dataset SOCRATES (ShOrtCut-fRee lATent rEaSoning). We observe that LLMs demonstrate promising latent multi-hop reasoning abilities without exploiting shortcuts, but only for certain types of queries. For queries requiring latent recall of countries as the intermediate answer, the best models achieve 80% latent composability, but this drops to just 5% for the recall of years. Comparisons with Chain-of-Thought composability highlight a significant gap between the ability of models to reason latently versus explicitly. Analysis reveals that latent representations of the intermediate answer are constructed more often in queries with higher latent composability, and shows the emergence of latent multi-hop reasoning during pretraining.

Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the input length to LLMs grows linearly, causing a dramatic increase in latency and a degradation in long-context understanding. This is particularly serious for multi-hop questions that require a chain of reasoning across documents. To accelerate inference, reduce costs, and minimize distractions, this paper presents BRIEF (Bridging Retrieval and Inference through Evidence Fusion), a lightweight approach that performs query-aware multi-hop reasoning by compressing retrieved documents into highly dense textual summaries to integrate into in-context learning. To enable learning compression for multi-hop reasoning, we curate synthetic data by extracting atomic proposition expressions that encapsulate distinct factoids from the source documents to compose synthetic summaries. Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries and enables a range of LLMs to achieve exceptional open-domain question answering (QA) performance. For example, on HotpotQA, BRIEF improves the compression rate by 2 times compared to the state-of-the-art baseline, while outperforming it by 3.00% EM and 4.16% F1 with Flan-UL2 as the reader LM. It also generates more concise summaries than proprietary GPT-3.5, while demonstrating nearly identical QA performance.

Large language models (LLMs) can solve complex multi-step problems, but little is known about how these computations are implemented internally. Motivated by this, we study how LLMs answer multi-hop queries such as "The spouse of the performer of Imagine is". These queries require two information extraction steps: a latent one for resolving the first hop ("the performer of Imagine") into the bridge entity (John Lennon), and one for resolving the second hop ("the spouse of John Lennon") into the target entity (Yoko Ono). Understanding how the latent step is computed internally is key to understanding the overall computation. By carefully analyzing the internal computations of transformer-based LLMs, we discover that the bridge entity is resolved in the early layers of the model. Then, only after this resolution, the two-hop query is solved in the later layers. Because the second hop commences in later layers, there could be cases where these layers no longer encode the necessary knowledge for correctly predicting the answer. Motivated by this, we propose a novel "back-patching" analysis method whereby a hidden representation from a later layer is patched back to an earlier layer. We find that in up to 57% of previously incorrect cases there exists a back-patch that results in the correct generation of the answer, showing that the later layers indeed sometimes lack the needed functionality. Overall our methods and findings open further opportunities for understanding and improving latent reasoning in transformer-based LLMs.

Relation extraction (RE) is a fundamental task in natural language processing, aiming to identify relations between target entities in text. While many RE methods are designed for a single sentence or document, cross-document RE has emerged to address relations across multiple long documents. Given the nature of long documents in cross-document RE, extracting document embeddings is challenging due to the length constraints of pre-trained language models. Therefore, we propose REward-based Input Construction (REIC), the first learning-based sentence selector for cross-document RE. REIC extracts sentences based on relational evidence, enabling the RE module to effectively infer relations. Since supervision of evidence sentences is generally unavailable, we train REIC using reinforcement learning with RE prediction scores as rewards. Experimental results demonstrate the superiority of our method over heuristic methods for different RE structures and backbones in cross-document RE. Our code is publicly available at https://github.com/aailabkaist/REIC.