arXiv subjects

Hyeongjun Yun

Publications and source records attributed to Hyeongjun Yun.

3 recordsLinked to original sources

arXiv2026

A Dual-Expert Strategy Integrating LLMs to Mitigate Negative Transfer in Cross-Domain Sequential Recommendation

Cross-Domain Sequential Recommendation (CDSR) predicts the next item a user will interact with based on their historical interaction sequences across multiple domains. Recent approaches leverage Large Language Models (LLMs) finetuned on textual representations of cross-domain user sequences to retrieve the recommended items, referred to as LLMRec. However, LLMRec primarily models the autoregressive patterns of token-level item texts, while overlooking item-level collaborative signals. This semantic misalignment often leads to distorted knowledge transfer across domains-termed negative transfer degrading performance in the CDSR task. To address this issue, we propose a novel LLM-based CDSR model, DuELRec: Domain-Gated Dual Experts with LLMs for Cross-Domain Sequential Recommendation. We propose a domain-gated dual-expert framework, equipped with an item-aware attention transformation module, which aggregates textual subtokens into item-level representations and enforces block-level attention masking. The single-domain expert restricts autoregressive attention to items within the same domain, while the cross-domain expert allows it across all domains. A gating mechanism adaptively fuses their outputs, using single-domain signals to reduce cross-domain noise that causes negative transfer. Second, we introduce a dual-sampling token-to-item contrastive learning objective that allows LLMs to capture the item-level collaborative signals from both single- and cross-domains. This is achieved by transforming token-level item texts into item-level representations and applying stochastic negative sampling from both single- and cross-domain item pools for contrastive learning. Extensive experiments on two real-world datasets across ten domains show that our model outperforms 26 state-of-the-art methods in recommendation performance.

cs.IR↗

arXiv2026

Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target

Generative LLM-based recommenders (LLM-Rec) require continual post-deployment updates, yet deployment logs provide only policy-shaped contextual bandit feedback: outcomes are observed solely for items exposed by a prior serving policy, inducing exposure bias and yielding partial, asymmetric signals consisting of relatively reliable positive responses and ambiguous no-responses. We propose an Anchored Bandit Policy Optimization (ABPO) framework for continual LLM-Rec updates that combines group-relative policy optimization (GRPO) with explicit treatment of exposure bias and feedback ambiguity. Specifically, we insert the exposed recommendation as a logged anchor into each GRPO rollout group, so that group-relative normalization is calibrated against the action actually exposed by the prior policy rather than against newly sampled rollouts alone. Because both positive- and no-responses are observed only through prior-policy exposure, we apply self-normalized inverse propensity scoring to the fixed anchor for both feedback types to correct for policy mismatch. At the same time, we treat the two feedback types asymmetrically in reliability: positive responses provide relatively direct endorsement signals, whereas no-responses remain ambiguous because they may reflect either true disinterest or unobserved external factors. To avoid overly aggressive updates from ambiguous no-responses, we temper their penalties with self-certainty, using the model's output-token confidence as a verifier-free reliability signal. Across five domains from Amazon Reviews and MovieLens, our method yields consistent post-update gains in recommendation accuracy while mitigating prior-policy-induced exposure bias more effectively than prior baselines.

cs.LG↗

arXiv2025

Towards Trustworthy LLM-Based Recommendation via Rationale Integration

Traditional recommender systems (RS) have been primarily optimized for accuracy and short-term engagement, often overlooking transparency and trustworthiness. Recently, platforms such as Amazon and Instagram have begun providing recommendation rationales to users, acknowledging their critical role in fostering trust and enhancing engagement; however, most existing systems still treat them as post-hoc artifacts. We propose an LLM-based recommender (LLM-Rec) that not only predicts items but also generates logically grounded rationales. Our approach leverages a self-annotated rationale dataset and instruction tuning in a rationale-first format, where the model generates an explanation before outputting the recommended item. By adopting this strategy and representing rationales in a chain-of-thought (CoT) style, LLM-Rec strengthens both interpretability and recommendation performance. Experiments on the Fashion and Scientific domains of the Amazon Review dataset demonstrate significant improvements over well-established baselines. To encourage reproducibility and future research, we publicly release a rationale-augmented recommendation dataset containing user histories, rationales, and recommended items.

cs.IR↗