Related papers: A Public Reference Implementation of the RAP Anaph…
Regular expression (RE) matching is a very common functionality that scans a text to find occurrences of patterns specified by an RE; it includes the simpler function of RE recognition. Here we address RE parsing, which subsumes matching by…
The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues. Private inference (PI) techniques using cryptographic primitives offer a solution but often have high computation and…
The accelerated proximal point algorithm (APPA), also known as "Catalyst", is a well-established reduction from convex optimization to approximate proximal point computation (i.e., regularized minimization). This reduction is conceptually…
Parametric Retrieval-Augmented Generation (PRAG) is a RAG approach that integrates external knowledge directly into model parameters using a LoRA adapter, aiming at reducing the inference cost compared to traditional RAG. However, current…
Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. Existing automatic prompt optimization(APO) frameworks target task accuracy exclusively…
Recent empirical studies show that the performance of GenProg is not satisfactory, particularly for Java. In this paper, we propose ARJA, a new GP based repair approach for automated repair of Java programs. To be specific, we present a…
The paper presents an overview of the third edition of the shared task on multilingual coreference resolution, held as part of the CRAC 2024 workshop. Similarly to the previous two editions, the participants were challenged to develop…
Machine unlearning, enabling a trained model to forget specific data, is crucial for addressing erroneous data and adhering to privacy regulations like the General Data Protection Regulation (GDPR)'s "right to be forgotten". Despite recent…
We present CorPipe, the winning entry to the CRAC 2023 Shared Task on Multilingual Coreference Resolution. Our system is an improved version of our earlier multilingual coreference pipeline, and it surpasses other participants by a large…
The high volume of published chemical patents and the importance of a timely acquisition of their information gives rise to automating information extraction from chemical patents. Anaphora resolution is an important component of…
Most previous studies on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b; Hou, 2018a) use the pairwise model to tackle the problem and assume that the gold mention information is given. In this paper, we cast bridging…
Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged…
In rank aggregation problems (RAP), the solution is usually a consensus ranking that generalizes a set of input orderings. There are different variants that differ not only in terms of the type of rankings that are used as input and output,…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…
In order to take steps towards establishing a methodology for evaluating Natural Language systems, we conducted a case study. We attempt to evaluate two different approaches to anaphoric processing in discourse by comparing the accuracy and…
A noun phrase can indirectly refer to an entity that has already been mentioned. For example, ``I went into an old house last night. The roof was leaking badly and ...'' indicates that ``the roof'' is associated with `` an old house}'',…
Product-specific community question answering platforms can greatly help address the concerns of potential customers. However, the user-provided answers on such platforms often vary a lot in their qualities. Helpfulness votes from the…
Language model reasoning traces are rarely all-or-nothing; they frequently contain valid intermediate steps before a critical error occurs. Existing uncertainty quantification methods typically certify final answers or entire responses,…
Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent interest as ASR use becomes more widespread. We are releasing contextual biasing lists to accompany the Earnings21 dataset, creating a public…
Automatic evaluation of retrieval augmented generation (RAG) systems relies on fine-grained dimensions like faithfulness and relevance, as judged by expert human annotators. Meta-evaluation benchmarks support the development of automatic…