Related papers: Parameter-Efficient Quality Estimation via Frozen …

Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and produces models whose token-level outputs are noise. We argue this is a missed…

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with…

Large Language Models (LLMs) typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. In particular, LLMs deployed on edge devices are memory-bound, and reducing…

Quality Estimation (QE) models for Neural Machine Translation (NMT) predict the quality of the hypothesis without having access to the reference. An emerging research direction in NMT involves the use of QE models, which have demonstrated…

Recursive partitioning methods provide computationally efficient surrogates for the Wasserstein distance, yet their statistical behavior and their resolution in the small-discrepancy regime remain insufficiently understood. We study…

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

Evaluating the quality of machine-generated natural language content is a challenging task in Natural Language Processing (NLP). Recently, large language models (LLMs) like GPT-4 have been employed for this purpose, but they are…

\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but its reliability under noisy retrieval contexts remains…

Machine translation quality estimation (QE) predicts human judgements of a translation hypothesis without seeing the reference. State-of-the-art QE systems based on pretrained language models have been achieving remarkable correlations with…

Most studies on word-level Quality Estimation (QE) of machine translation focus on language-specific models. The obvious disadvantages of these approaches are the need for labelled data for each language pair and the high cost required to…

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of…

Quality estimation (QE) plays a crucial role in machine translation (MT) workflows, as it serves to evaluate generated outputs that have no reference translations and to determine whether human post-editing or full retranslation is…

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM…

Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which…

We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have…

Neural language models (LMs) have been proved to significantly outperform classical n-gram LMs for language modeling due to their superior abilities to model long-range dependencies in text and handle data sparsity problems. And recently,…

Providing quality scores along with Machine Translation (MT) output, so-called reference-free Quality Estimation (QE), is crucial to inform users about the reliability of the translation. We propose a model-specific, unsupervised QE…

Current state-of-the-art relation extraction methods typically rely on a set of lexical, syntactic, and semantic features, explicitly computed in a pre-processing step. Training feature extraction models requires additional annotated…

Neural machine translation systems estimate probabilities of target sentences given source sentences, yet these estimates may not align with human preferences. This work introduces QE-fusion, a method that synthesizes translations using a…

As large language models (LLMs) become more prevalent, there is a growing need for new and improved quantization methods that can meet the computationalast layer demands of these modern architectures while maintaining the accuracy. In this…