Related papers: In-Context Editing: Learning Knowledge from Self-I…

The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence embedding methods, it remains unclear as how to best modify a sentence embedding conditioned on its context. To address…

Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guidelines such as the \emph{Right to be Forgotten}. Achieving…

With the increasing ability of large language models (LLMs), in-context learning (ICL) has evolved as a new paradigm for natural language processing (NLP), where instead of fine-tuning the parameters of an LLM specific to a downstream task…

Constraint modelling languages such as Essence offer a means to describe combinatorial problems at a high-level, i.e., without committing to detailed modelling decisions for a particular solver or solving paradigm. Given a problem…

A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for…

Existing locate-then-edit Knowledge Editing (KE) methods typically decompose editing into two stages: upstream target representation optimization and downstream constrained parameter optimization. The optimization across the two stages is…

We consider the problem of single-source domain generalization. Existing methods typically rely on extensive augmentations to synthetically cover diverse domains during training. However, they struggle with semantic shifts (e.g., background…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Frequently updating Large Language Model (LLM)-based recommender systems to adapt to new user interests -- as done for traditional ones -- is impractical due to high training costs, even with acceleration methods. This work explores…

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training,…

Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly…

In-context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance can be critically sensitive to the choice of examples. To…

Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks. However, existing works have shown that the effectiveness of ICL is highly sensitive…

We present EDGE, a general-purpose, misconception-aware adaptive learning framework composed of four stages: Evaluate (ability and state estimation), Diagnose (posterior infer-ence of misconceptions), Generate (counterfactual item…

Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing…

Context distillation enables language models to internalize in-context knowledge into their parameters. In our work, we propose On-Policy Context Distillation (OPCD), a framework that bridges on-policy distillation with context distillation…

Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we…

Fine-tuning large language models is becoming ever more impractical due to their rapidly-growing scale. This motivates the use of parameter-efficient adaptation methods such as prompt tuning (PT), which adds a small number of tunable…

Speech style editing refers to modifying the stylistic properties of speech while preserving its linguistic content and speaker identity. However, most existing approaches depend on explicit labels or reference audio, which limits both…