United States

As part of the AVeriTeC shared task, we developed a pipelined system comprising robust and finely tuned models. Our system integrates advanced techniques for evidence retrieval and question generation, leveraging cross-encoders and large language models (LLMs) for optimal performance. With multi-stage processing, the pipeline demonstrates improvements over baseline models, particularly in handling complex claims that require nuanced reasoning by improved evidence extraction, question generation and veracity prediction. Through detailed experiments and ablation studies, we provide insights into the strengths and weaknesses of our approach, highlighting the critical role of evidence sufficiency and context dependency in automated fact-checking systems. Our system secured a competitive rank, 7th on the development and 12th on the test data, in the shared task, underscoring the effectiveness of our methods in addressing the challenges of real-world claim verification.

EMNLP 2024

SK_DU Team: Cross-Encoder based Evidence Retrieval and Question Generation with Improved Prompt for the AVeriTeC Shared Task

automated fact verification

evidence extraction

llms

reranking

question generation

cross-encoder

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

We present the Information-Retrieving Fact-Checker (InFact), the fact-checking system which won the AVeriTeC shared task. InFact is an LLM-based 6-stage pipeline. It performs best with GPT-4o.

InFact: A Strong Baseline for Automated Fact-Checking

Automated Fact-Checking (AFC) has recently gained considerable attention to address the increasing misinformation spreading in the web and social media. The recently introduced AVeriTeC dataset alleviates some limitations of existing AFC benchmarks. In this paper, we propose to explore Retrieval Augmented Generation (RAG) and describe the system (UPS participant) we implemented to solve the AVeriTeC shared task. Our end-to-end system integrates retrieval and generation in a joint training setup to enhance evidence retrieval and question generation. Our system operates as follows: First, we conduct dense retrieval of evidence by encoding candidate evidence sentences from the provided knowledge store documents. Next, we perform a secondary retrieval of question-answer pairs from the training set, encoding these into dense vectors to support question generation with relevant in-context examples. During training, the question generator is optimized to generate questions based on retrieved or gold evidence. In preliminary automatic evaluation, our system achieved respectively 0.198 and 0.210 AVeriTeC scores on the dev and test sets.

Exploring Retrieval Augmented Generation For Real-world Claim Verification

In the information era, the vast proliferation of online content poses significant challenges, particularly concerning the trustworthiness of these digital statements, which can have profound societal implications. Although it is possible to manually annotate and verify the authenticity of such content, the sheer volume and rapid pace of information generation render this approach impractical, both in terms of time and cost. Therefore, it is imperative to develop automated systems capable of validating online claims, ensuring that users can use the wealth of information available on the Internet effectively and reliably. Using primarily ChatGPT and the Google search API, GProofT fact checking framework generates question-answer pairs to systematically extract and verify the facts within claims. Based on the outcomes of these QA pairs, claims are subsequently labeled as Supported, Conflicted Evidence/Cherry-Picking, or Refuted. Shown by extensive experiments, GProofT Retrieval generally performs effectively in fact-checking and makes a substantial contribution to the task.

GProofT: A Multi-dimension Multi-round Fact Checking Framework Based on Claim Fact Extraction

To tackle the AVeriTeC shared task hosted by the FEVER-24, we introduce a system that only employs publicly available large language models (LLMs) for each step of automated fact-checking, dubbed the Herd of Open LLMs for verifying real-world claims (HerO). For evidence retrieval, a language model is used to enhance a query by generating hypothetical fact-checking documents. We prompt pretrained and fine-tuned LLMs for question generation and veracity prediction by crafting prompts with retrieved in-context samples. HerO achieved 2nd place on the leaderboard with the AVeriTeC score of 0.57, suggesting the potential of open LLMs for verifying real-world claims. For future research, we make our code publicly available

The Herd of Open LLMs for Verifying Real-World Claims

Our paper and presentation describe our 3rd place submission in the AVeriTeC shared task in which we attempted to address the challenge of fact-checking with evidence retrieved in the wild using a simple scheme of Retrieval-Augmented Generation (RAG) designed for the task, leveraging the predictive power of Large Language Models. We release our codebase and explain its two modules - the Retriever and the Evidence & Label generator - in detail, justifying their features such as MMR-reranking and Likert-scale confidence estimation. We evaluate our solution on AVeriTeC dev and test set and interpret the results, picking the GPT-4o as the most appropriate model for our pipeline at the time of our publication, with Llama 3.1 70B being a promising open-source alternative. We perform an empirical error analysis to see that faults in our predictions often coincide with noise in the data or ambiguous fact-checks, provoking further research and data augmentation.

AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task

The ability to extract and verify factual information from free-form text is critical in an era where vast amounts of unstructured data are available, yet unreliable sources abound. This paper focuses on enhancing causal deductive reasoning, a key component of factual verification, through the lens of accident investigation, where determining the probable causes of events is paramount. Deductive reasoning refers to the task of drawing conclusions based on a premise. While some deductive reasoning benchmarks exist, none focus on causal deductive reasoning and are from real-world applications. Recently, large language models (LLMs) used with prompt engineering techniques like retrievalaugmented generation (RAG) have demonstrated remarkable performance across various natural language processing benchmarks. However, adapting these techniques to handle scenarios with no knowledge bases and to different data structures, such as graphs, remains an ongoing challenge. In our study, we introduce a novel framework leveraging LLMs’ decent ability to detect and infer causal relations to construct a causal Knowledge Graph (KG) which represents knowledge that the LLM recognizes. Additionally, we propose a RoBERTa-based Transformer Graph Neural Network (RoTG) specifically designed to select relevant nodes within this KG. Integrating RoTG-retrieved causal chains into prompts effectively enhances LLM performance, demonstrating usefulness of our approach in advancing LLMs’ causal deductive reasoning capabilities.

Enhancing Fact Verification with Causal Knowledge Graphs and Transformer-Based Retrieval for Deductive Reasoning

In this paper, we investigate the influence of claims in analyst reports and earnings calls on financial market returns, considering them as significant quarterly events for publicly traded companies. To facilitate a comprehensive analysis, we construct a new financial dataset for the claim detection task in the financial domain. We benchmark various language models on this dataset and propose a novel weak-supervision model that incorporates the knowledge of subject matter experts (SMEs) in the aggregation function, outperforming existing approaches. We also demonstrate the practical utility of our proposed model by constructing a novel measure of optimism. Here, we observe the dependence of earnings surprise and return on our optimism measure. Our dataset, models, and code are publicly (under CC BY 4.0 license) available on GitHub.

Numerical Claim Detection in Finance: A New Financial Dataset, Weak-Supervision Model, and Market Analysis

Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information, yet existing approaches produce large-sized sets, incurring high computational costs and slow response times. In this work, we introduce a score refinement method that applies a simple monotone transformation to retrieval scores, leading to significantly smaller conformal sets while maintaining their statistical guarantees. Experiments on various BEIR benchmarks validate the effectiveness of our approach in producing compact sets containing relevant information.

Streamlining Conformal Information Retrieval via Score Refinement

Most existing fact-checking systems are unable to explain their decisions by providing relevant rationales (justifications) for their predictions. It highlights a lack of transparency that poses significant risks, such as the prevalence of unexpected biases, which may increase political polarization due to limitations in impartiality. To address this critical gap, we introduce Sentence-Level Factual Reasoning (SELFAR) aimed at improving explainable fact-checking. SELFAR relies on fact extraction and verification by predicting the news source reliability and factuality (veracity) of news articles or claims at the sentence level, generating post-hoc explanations using SHAP/LIME and zero-shot prompts. Our experiments show that unreliable news stories predominantly consist of subjective statements, in contrast to reliable ones. Consequently, predicting unreliable news articles at the sentence level by analyzing impartiality and subjectivity is a promising approach for fact extraction and improving explainable fact-checking. Furthermore, LIME outperforms SHAP in explaining predictions on reliability. Additionally, while zero-shot prompts provide highly readable explanations and achieve an accuracy of 0.71 in predicting factuality, their tendency to hallucinate remains a challenge. Lastly, this paper also presents the first study on explainable fact-checking in the Portuguese language.

Improve Explainable Fact-Checking via Sentence-Level Factual Reasoning

Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit performance, as incorrect chunks can lead the synthesizer LLM to generate a false response. This work applies a zero-shot adaptation of standard dense retrieval steps for more accurate chunk recall. Specifically, a chunk is first decomposed into atomic statements. A set of synthetic questions are then generated on these atoms (with the chunk as the context). Dense retrieval involves finding the closest set of synthetic questions, and associated chunks, to the user query. It is found that retrieval with the atoms leads to higher recall than retrieval with chunks. Further performance gain is observed with retrieval using the synthetic questions generated over the atoms. Higher recall at the retrieval step enables higher performance of the enterprise LLM using the RAG pipeline.

Downloads

Next from EMNLP 2024

InFact: A Strong Baseline for Automated Fact-Checking

Similar lecture

Exploring Retrieval Augmented Generation For Real-world Claim Verification