English
Related papers

Related papers: The Alignment Bottleneck in Decomposition-Based Cl…

200 papers

Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on brittle formal logic. However, progress in this direction has…

The decompose-then-verify strategy for verification of Large Language Model (LLM) generations decomposes claims that are then independently verified. Decontextualization augments text (claims) to ensure it can be verified outside of the…

Computation and Language · Computer Science 2024-12-18 Miriam Wanner , Benjamin Van Durme , Mark Dredze

Lexical and semantic matches are commonly used as relevance measurements for information retrieval. Together they estimate the semantic equivalence between the query and the candidates. However, semantic equivalence is not the only…

Computation and Language · Computer Science 2023-11-07 Fan Luo , Mihai Surdeanu

Claim verification is a task that involves assessing the truthfulness of a given claim based on multiple evidence pieces. Using large language models (LLMs) for claim verification is a promising way. However, simply feeding all the evidence…

Computation and Language · Computer Science 2024-07-18 Haisong Gong , Huanhuan Ma , Qiang Liu , Shu Wu , Liang Wang

Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation and hallucination detection, motivating a growing interest in efficient probe-based approaches. Yet it remains unclear…

Computation and Language · Computer Science 2026-04-14 Joe Stacey , Hadas Orgad , Kentaro Inui , Benjamin Heinzerling , Nafise Sadat Moosavi

Accurate evidence retrieval is essential for automated fact checking. Little previous research has focused on the differences between true and false claims and how they affect evidence retrieval. This paper shows that, compared with true…

Information Retrieval · Computer Science 2021-12-15 Mingwen Dong , Christos Christodoulopoulos , Sheng-Min Shih , Xiaofei Ma

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

Machine Learning · Computer Science 2022-10-25 Sumedha Singla , Nihal Murali , Forough Arabshahi , Sofia Triantafyllou , Kayhan Batmanghelich

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an…

Computation and Language · Computer Science 2021-05-17 Haoran Li , Arash Einolghozati , Srinivasan Iyer , Bhargavi Paranjape , Yashar Mehdad , Sonal Gupta , Marjan Ghazvininejad

In reality, learning from multi-view multi-label data inevitably confronts three challenges: missing labels, incomplete views, and non-aligned views. Existing methods mainly concern the first two and commonly need multiple assumptions to…

Machine Learning · Computer Science 2024-06-12 Xiang Li , Songcan Chen

Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Patrick Schmidt , Vasileios Belagiannis , Lazaros Nalpantidis

A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies that constrain what can validly follow. Existing approaches typically model only one of…

Computation and Language · Computer Science 2026-05-29 David Busbib , Michael Werman

The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the…

Computation and Language · Computer Science 2025-12-25 Matyas Bohacek , Nino Scherrer , Nicholas Dufour , Thomas Leung , Christoph Bregler , Stephanie C. Y. Chan

How many labeled examples are needed to estimate a classifier's performance on a new dataset? We study the case where data is plentiful, but labels are expensive. We show that by making a few reasonable assumptions on the structure of the…

Machine Learning · Computer Science 2012-10-09 Peter Welinder , Max Welling , Pietro Perona

Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query, and extracting and citing evidence spans helps improve the trustworthiness of these summaries. Whereas previous work has…

Computation and Language · Computer Science 2025-10-31 Dustin Wright , Zain Muhammad Mujahid , Lu Wang , Isabelle Augenstein , David Jurgens

Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions and structured tabular data. However, previous table-based…

Computation and Language · Computer Science 2023-04-28 Yunhu Ye , Binyuan Hui , Min Yang , Binhua Li , Fei Huang , Yongbin Li

Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly must be better at assembling facts. We show that this…

Artificial Intelligence · Computer Science 2026-05-27 Zhe Yu , Wenpeng Xing , Yunzhao Wei , Jie Chen , Hongzhi Wang , Xuyang Teng , Meng Han

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Rongchang Xie , Chunyu Wang , Wenjun Zeng , Yizhou Wang

Automated fact extraction and verification is a challenging task that involves finding relevant evidence sentences from a reliable corpus to verify the truthfulness of a claim. Existing models either (i) concatenate all the evidence…

Computation and Language · Computer Science 2020-10-13 Shyam Subramanian , Kyumin Lee

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi

To inhibit the spread of rumorous information and its severe consequences, traditional fact checking aims at retrieving relevant evidence to verify the veracity of a given claim. Fact checking methods typically use knowledge graphs (KGs) as…

Artificial Intelligence · Computer Science 2024-07-30 Shuai Wang , Penghui Wei , Qingchao Kong , Wenji Mao