TriviaQA

anchor

Findings

• IC-034Benefit and detriment in RAG can be traded off at token level for Llama-2, OPT and Mistral using representation similarity [eval]
• IC-1007LLMs cannot reliably self-verify or self-correct their own outputs without external tool feedback [eval]
• IC-1319Larger LLaMA and LLaMA2 models show better calibration on phrase-level tasks but not consistently on sentence- and paragraph-level tasks [eval]
• IC-1386Fact recall in OPT and LLaMA models degrades by more than 5% relative accuracy when more than 30% of weights are pruned, and similarly when moving from the 30B to the 13B dense model [eval]
• IC-1387In-context learning capabilities in OPT and LLaMA models remain within 5% of dense-model accuracy even at 60-70% sparsity, and show less than 2% difference between the 30B and 1.3B dense OPT models [eval]
• IC-1388In LLaMA-13B, feed-forward layers are more critical than attention layers for fact recall, while both are equally important for in-context learning [eval]
• IC-1523Five AI assistants (Claude-1.3, Claude-2.0, GPT-3.5-turbo, GPT-4, Llama-2-70B-Chat) consistently exhibit sycophancy across four varied free-form text-generation tasks [eval]
• IC-177GPT-4o mini, GPT-4o, and Llama-3-8B all over-rely on incorrect external context, producing wrong answers at high rates when the context conflicts with their internal knowledge [eval]
• IC-178Self-guided confidence reasoning (SCR) outperforms rule-based confidence reasoning (RCR) for GPT-4o and GPT-4o mini, but RCR outperforms SCR for Llama-3-8B [eval]
• IC-179GPT-4o mini, GPT-4o, and Llama-3-8B all calibrate confidence in their internal answers significantly better than confidence in external contexts [eval]
• IC-180GPT-4o-mini's resistance to incorrect context depends on the position of the context relative to the question in the prompt [eval]
• IC-181Truthfulness in Mistral-7B, Mistral-7B-Instruct, Llama3-8B, and Llama3-8B-Instruct is linearly decodable from internal representations at exact answer tokens, with middle-to-late layers being most informative [eval]
• IC-182Truthfulness encoding in Mistral-7B, Mistral-7B-Instruct, Llama3-8B, and Llama3-8B-Instruct is skill-specific rather than universal; probing classifiers do not meaningfully generalize across different task types beyond logit-based baselines [eval]
• IC-183Error types in Mistral-7B, Mistral-7B-Instruct, Llama3-8B, and Llama3-8B-Instruct are linearly predictable from internal representations, encoding fine-grained information beyond binary correctness [eval]
• IC-184Mistral-7B, Mistral-7B-Instruct, Llama3-8B, and Llama3-8B-Instruct can internally encode the correct answer while externally generating an incorrect one, with the discrepancy most pronounced for error types where the model shows no external preference for the correct answer [eval]
• IC-264All 18 evaluated LLMs fail to abstain when the provided context lacks the answer, with performance gaps of 13.6% to 68.4% relative to the original context [source]
• IC-265Model families show extreme variation in detecting conflicting answers in inconsistent contexts, with phi-3 series at 5.8% average accuracy versus GPT-4 series at 89.35% [source]
• IC-282GPT-2 XL (1.5B) exhibits lower accuracy but reduced overconfidence (smaller ECE and Brier scores) compared to larger models on the CAT benchmark [eval]
• IC-592The log-likelihood layer in LLaMA-2-7B, LLaMA-2-7B-Chat, Vicuna-7B, and Mistral-7B-Instruct produces factually incorrect answers on TruthfulQA MC1 (817 samples) due to a misalignment between the output distribution and internal attention head representations, with LM-to-head-norm accuracy gaps of 24.23 to 40.68 points. [eval]
• IC-748Pruned LLMs at ≥50% sparsity remain robust in-context retrievers and summarizers, with Vicuna-7B matching up to ~40% sparsity and Vicuna-13B up to ~50% sparsity in open-book settings [eval]