Generative recommenders decode items from a user's interaction history, but offer no way for users to correct a recommendation that misses their current intent. Adding conversation is natural since items and words share same output space, yet training the model to converse may overwrite the history-to-item mapping it r...
Yuliia Den, Zhi Rui Tam, Yung-Yu Shih et al.· 0 citations
Model merging aims to build a multi-task model cheaply by combining the weights of individual task-specific models. To perform well across multiple tasks, most existing merging methods use an additional dataset to find the coefficients for the best linear combination of task-specific weight updates. However, we identif...
Sin-Han Yang, Shih-Cheng Huang, Chieh-Yen Lin et al.· 0 citations
Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, finding optimal merging coefficients requires an extensive search that becomes prohibitively expensive as models scale in both size and number, due to high memory requiremen...
Shih-Cheng Huang, Zhi Rui Tam, Chieh-Yen Lin et al.· 0 citations
Rapid progress in video generation has led to a plethora of models that differ substantially in capability and generation cost. This raises a natural question: can each request be efficiently routed to an appropriate model? We find that even when the consensus of the other annotators is used as an oracle, it agrees wit...
Zhi Rui Tam, Chao-Chung Wu, Sin-Han Yang et al.· 0 citations
Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can bridge vocabulary gaps with the target corpus. Any single LLM, however, is limited by its training data and architectural biases, and its enrichment behavior depends on h...
Tzu-I Ho, Yung-Yu Shih, Shang-Yu Su et al.· 0 citations
Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on response-level confidence, which estimates the correctness of a single generated output. However, this formulation is misaligned with many practical settings where the central qu...
A three-stage evaluation pipeline is designed that progressively reduces textual guidance to systematically evaluate LALMs' in-context learning ability in the audio modality, uncovering a consistent asymmetry across LALMs.
Yen-Ting Piao, Jay Chiehen Liao, W. Chien et al.· 1 citation
Experiments on an LLM-generated fake news benchmark show that RADAR outperforms retrieval-augmented trainable baselines and general-purpose LLMs with retrieval, suggesting improved generalization beyond the specific co-evolved generator used during training.
Song-Duo Ma, Yi-Hung Liu, Hsin-Yu Lin et al.· 0 citations
Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existing in-context learning-based methods fail to capture how individuals react under different situations. In addition, LLM-based evaluation is difficult for obscure individua...
Jinjun Peng, Yi-Zhen Zhang, Chun-Nan Chou et al.· 0 citations
Tri-PvP, an 8,000-sample tri-modal conflict benchmark crossing vision, audio, and text, is introduced, revealing a systematic asymmetry in evidence-form bias: models exhibit a stronger bias toward perceptual signal in vision but propositional in audio.
Yen-Ting Piao, Shu-Yun Chen, Chin-Hui Chu et al.· 0 citations
Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primarily evaluate memory through QA-style probing rather than in-situ conversational usage. We introduce LOCOMO-CONV, a conversa- tional memory b...
AdaSearch is proposed, a simple two-stage, outcome-driven RL framework that disentangles problem-solving from the decision to search, making the decision process explicit and interpretable and significantly improves search-decision quality and reduces unnecessary search calls.
Tzu-Han Lin, Wei-Lin Chen, Chen-An Li et al.· arXiv.org· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
